agora inbox for [email protected]help / color / mirror / Atom feed
[PATCH] Restructure repack worker teardown 496+ messages / 2 participants [nested] [flat]
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH] Restructure repack worker teardown @ 2026-05-18 17:13 Álvaro Herrera <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Álvaro Herrera @ 2026-05-18 17:13 UTC (permalink / raw) The original code would leave a shared memory segment unreleased if we fail partway through initialization. Change the shutdown order so that we already free it. Author: Álvaro Herrera <[email protected]> Discussion: https://postgr.es/m/[email protected] --- src/backend/commands/repack.c | 67 ++++++++++++++++------------------- 1 file changed, 31 insertions(+), 36 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index bfc62c8f752..c9064d8fd13 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -3411,10 +3411,14 @@ start_repack_decoding_worker(Oid relid) shm_mq_handle *mqh; BackgroundWorker bgw; + decoding_worker = palloc0_object(DecodingWorker); + /* Setup shared memory. */ size = BUFFERALIGN(offsetof(DecodingWorkerShared, error_queue)) + BUFFERALIGN(REPACK_ERROR_QUEUE_SIZE); seg = dsm_create(size, 0); + decoding_worker->seg = seg; + shared = (DecodingWorkerShared *) dsm_segment_address(seg); shared->initialized = false; shared->lsn_upto = InvalidXLogRecPtr; @@ -3454,14 +3458,12 @@ start_repack_decoding_worker(Oid relid) bgw.bgw_main_arg = UInt32GetDatum(dsm_segment_handle(seg)); bgw.bgw_notify_pid = MyProcPid; - decoding_worker = palloc0_object(DecodingWorker); if (!RegisterDynamicBackgroundWorker(&bgw, &decoding_worker->handle)) ereport(ERROR, errcode(ERRCODE_CONFIGURATION_LIMIT_EXCEEDED), errmsg("out of background worker slots"), errhint("You might need to increase \"%s\".", "max_worker_processes")); - decoding_worker->seg = seg; decoding_worker->error_mqh = mqh; /* @@ -3487,17 +3489,6 @@ start_repack_decoding_worker(Oid relid) ConditionVariableCancelSleep(); } -/* - * PG_ENSURE_ERROR_CLEANUP callback to stop the decoding worker. - * This ensures the worker is terminated on both ERROR and FATAL exits, - * unlike PG_FINALLY which only handles ERROR. - */ -static void -repack_decoding_worker_cleanup_cb(int code, Datum arg) -{ - stop_repack_decoding_worker(); -} - /* * Stop the decoding worker and cleanup the related resources. * @@ -3508,39 +3499,43 @@ static void stop_repack_decoding_worker(void) { BgwHandleStatus status; + dsm_segment *dsmseg; - /* Haven't reached the worker startup? */ + /* Nothing to do if no worker was set up. */ if (decoding_worker == NULL) return; - /* Could not register the worker? */ - if (decoding_worker->handle == NULL) - return; + /* Terminate the worker process, if one is running. */ + if (decoding_worker->handle != NULL) + { + TerminateBackgroundWorker(decoding_worker->handle); + /* The worker should really exit before the REPACK command does. */ + HOLD_INTERRUPTS(); + status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); + RESUME_INTERRUPTS(); - TerminateBackgroundWorker(decoding_worker->handle); - /* The worker should really exit before the REPACK command does. */ - HOLD_INTERRUPTS(); - status = WaitForBackgroundWorkerShutdown(decoding_worker->handle); - RESUME_INTERRUPTS(); - - if (status == BGWH_POSTMASTER_DIED) - ereport(FATAL, - errcode(ERRCODE_ADMIN_SHUTDOWN), - errmsg("postmaster exited during REPACK command")); - - shm_mq_detach(decoding_worker->error_mqh); + if (status == BGWH_POSTMASTER_DIED) + ereport(FATAL, + errcode(ERRCODE_ADMIN_SHUTDOWN), + errmsg("postmaster exited during REPACK command")); + } /* - * If we could not cancel the current sleep due to ERROR, do that before - * we detach from the shared memory the condition variable is located in. - * If we did not, the bgworker ERROR handling code would try and fail - * badly. + * Now detach from our shared memory segment. In error cases there might + * still be messages from the worker in the queue, which ProcessInterrupts + * would try to read; this is pointless (and causes an assertion failure), + * so set the global pointer to NULL to have ProcessRepackMessages ignore + * them. */ - ConditionVariableCancelSleep(); - - dsm_detach(decoding_worker->seg); + dsmseg = decoding_worker->seg; pfree(decoding_worker); decoding_worker = NULL; + + /* We must also cancel the current sleep, if one is still set up */ + ConditionVariableCancelSleep(); + + if (dsmseg != NULL) + dsm_detach(dsmseg); } /* stop_repack_decoding_worker, wrapped as a before_shmem_exit callback */ -- 2.47.3 --b42ct6adeyjj4cbm-- ^ permalink raw reply [nested|flat] 496+ messages in thread
* [PATCH 7/8] Decouple updating of freezing information from swap_relation_files(). @ 2026-06-16 11:54 Antonin Houska <[email protected]> 0 siblings, 0 replies; 496+ messages in thread From: Antonin Houska @ 2026-06-16 11:54 UTC (permalink / raw) So far, the relfrozenxid and relminmxid attributes of pg_class used to be updated by swap_relation_files(), however, not every call of the function should do that. On the contrary, new feature of REPACK (CONCURRENTLY) will need to update this information in one case that would be tricky to handle using swap_relation_files(). --- src/backend/commands/repack.c | 114 +++++++++++++++++----------------- 1 file changed, 56 insertions(+), 58 deletions(-) diff --git a/src/backend/commands/repack.c b/src/backend/commands/repack.c index 6f3e4ecff46..92c1b678e6f 100644 --- a/src/backend/commands/repack.c +++ b/src/backend/commands/repack.c @@ -186,6 +186,8 @@ static void copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldInde TransactionId *pFreezeXid, MultiXactId *pCutoffMulti, ChangeContext *chgcxt); +static void update_relation_cutoffs(Oid relid, TransactionId frozenXid, + MultiXactId cutoffMulti); static List *get_tables_to_repack(RepackCommand cmd, bool usingindex, MemoryContext permcxt); static List *get_tables_to_repack_partitioned(RepackCommand cmd, @@ -2014,13 +2016,6 @@ copy_table_data(Relation NewHeap, Relation OldHeap, Relation OldIndex, * links) while the latter is the only way to handle cases in which a toast * table is added or removed altogether. * - * Additionally, the first relation is marked with relfrozenxid set to - * frozenXid. It seems a bit ugly to have this here, but the caller would - * have to do it anyway, so having it here saves a heap_update. Note: in - * the swap-toast-links case, we assume we don't need to change the toast - * table's relfrozenxid: the new version of the toast table should already - * have relfrozenxid set to RecentXmin, which is good enough. - * * Lastly, if r2 and its toast table and toast index (if any) are mapped, * their OIDs are emitted into mapped_tables[]. This is hacky but beats * having to look the information up again later in finish_heap_swap. @@ -2029,9 +2024,7 @@ static void swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, bool swap_toast_by_content, bool is_internal, - TransactionId frozenXid, - MultiXactId cutoffMulti, - Oid *mapped_tables) + Oid *mapped_tables, Oid *r1_toastid) { Relation relRelation; HeapTuple reltup1, @@ -2063,6 +2056,9 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, relam1 = relform1->relam; relam2 = relform2->relam; + if (r1_toastid) + *r1_toastid = relform1->reltoastrelid; + if (RelFileNumberIsValid(relfilenumber1) && RelFileNumberIsValid(relfilenumber2)) { @@ -2178,15 +2174,6 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, * and then fail to commit the pg_class update. */ - /* set rel1's frozen Xid and minimum MultiXid */ - if (relform1->relkind != RELKIND_INDEX) - { - Assert(!TransactionIdIsValid(frozenXid) || - TransactionIdIsNormal(frozenXid)); - relform1->relfrozenxid = frozenXid; - relform1->relminmxid = cutoffMulti; - } - /* swap size statistics too, since new rel has freshly-updated stats */ { int32 swap_pages; @@ -2288,9 +2275,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, target_is_pg_class, swap_toast_by_content, is_internal, - frozenXid, - cutoffMulti, - mapped_tables); + mapped_tables, + NULL); } else { @@ -2391,9 +2377,8 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, target_is_pg_class, swap_toast_by_content, is_internal, - InvalidTransactionId, - InvalidMultiXactId, - mapped_tables); + mapped_tables, + NULL); } /* Clean up. */ @@ -2403,6 +2388,36 @@ swap_relation_files(Oid r1, Oid r2, bool target_is_pg_class, table_close(relRelation, RowExclusiveLock); } +/* + * Update relfrozenxid and relminmxid attributes of pg_class entry, specified + * by OID. + */ +static void +update_relation_cutoffs(Oid relid, TransactionId frozenXid, + MultiXactId cutoffMulti) +{ + Relation relRelation; + HeapTuple reltup; + Form_pg_class relform; + CatalogIndexState indstate; + + relRelation = table_open(RelationRelationId, RowExclusiveLock); + reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid)); + if (!HeapTupleIsValid(reltup)) + elog(ERROR, "cache lookup failed for relation %u", relid); + relform = (Form_pg_class) GETSTRUCT(reltup); + relform->relfrozenxid = frozenXid; + relform->relminmxid = cutoffMulti; + + indstate = CatalogOpenIndexes(relRelation); + CatalogTupleUpdateWithInfo(relRelation, &reltup->t_self, reltup, + indstate); + CatalogCloseIndexes(indstate); + + heap_freetuple(reltup); + table_close(relRelation, RowExclusiveLock); +} + /* * Remove the transient table that was built by make_new_heap, and finish * cleaning up (including rebuilding all indexes on the old heap). @@ -2420,6 +2435,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, { ObjectAddress object; Oid mapped_tables[4]; + Oid oid_old_toastid; int i; /* Report that we are now swapping relation files */ @@ -2436,7 +2452,7 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, swap_relation_files(OIDOldHeap, OIDNewHeap, (OIDOldHeap == RelationRelationId), swap_toast_by_content, is_internal, - frozenXid, cutoffMulti, mapped_tables); + mapped_tables, &oid_old_toastid); /* * If it's a system catalog, queue a sinval message to flush all catcaches @@ -2492,37 +2508,20 @@ finish_heap_swap(Oid OIDOldHeap, Oid OIDNewHeap, PROGRESS_REPACK_PHASE_FINAL_CLEANUP); /* - * If the relation being rebuilt is pg_class, swap_relation_files() - * couldn't update pg_class's own pg_class entry (check comments in - * swap_relation_files()), thus relfrozenxid was not updated. That's - * annoying because a potential reason for doing a VACUUM FULL is a - * imminent or actual anti-wraparound shutdown. So, now that we can - * access the new relation using its indices, update relfrozenxid. - * pg_class doesn't have a toast relation, so we don't need to update the - * corresponding toast relation. Not that there's little point moving all - * relfrozenxid updates here since swap_relation_files() needs to write to - * pg_class for non-mapped relations anyway. + * Update relfrozenxid and relminmxid. CCI is needed to see the most + * recent pg_class tuple, created by swap_relation_files(). However that + * CCI makes us use the new relation file. Therefore we cannot do this + * before indexes have been rebuilt too. */ - if (OIDOldHeap == RelationRelationId) - { - Relation relRelation; - HeapTuple reltup; - Form_pg_class relform; - - relRelation = table_open(RelationRelationId, RowExclusiveLock); - - reltup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(OIDOldHeap)); - if (!HeapTupleIsValid(reltup)) - elog(ERROR, "cache lookup failed for relation %u", OIDOldHeap); - relform = (Form_pg_class) GETSTRUCT(reltup); - - relform->relfrozenxid = frozenXid; - relform->relminmxid = cutoffMulti; - - CatalogTupleUpdate(relRelation, &reltup->t_self, reltup); + CommandCounterIncrement(); + update_relation_cutoffs(OIDOldHeap, frozenXid, cutoffMulti); - table_close(relRelation, RowExclusiveLock); - } + /* + * The same for TOAST, if needed. In the swap-toast-links case, the new + * the toast table should already have relfrozenxid set to RecentXmin. + */ + if (OidIsValid(oid_old_toastid) && swap_toast_by_content) + update_relation_cutoffs(oid_old_toastid, frozenXid, cutoffMulti); /* Destroy new heap with old filenumber */ object.classId = RelationRelationId; @@ -4072,9 +4071,8 @@ rebuild_relation_finish_concurrent(Relation NewHeap, Relation OldHeap, (old_table_oid == RelationRelationId), false, /* swap_toast_by_content */ true, - InvalidTransactionId, - InvalidMultiXactId, - mapped_tables); + mapped_tables, + NULL); #ifdef USE_ASSERT_CHECKING -- 2.52.0 --=-=-= Content-Type: text/plain Content-Disposition: attachment; filename=v01-0008-Make-REPACK-CONCURRENTLY-MVCC-safe.patch ^ permalink raw reply [nested|flat] 496+ messages in thread
end of thread, other threads:[~2026-06-16 11:54 UTC | newest] Thread overview: 496+ messages (download: mbox mbox.gz follow: Atom feed) -- links below jump to the message on this page -- 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-05-18 17:13 [PATCH] Restructure repack worker teardown Álvaro Herrera <[email protected]> 2026-06-16 11:54 [PATCH 7/8] Decouple updating of freezing information from swap_relation_files(). Antonin Houska <[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