From d5dfb692c247cdcff03e07e0f963d6eb9b512c5f Mon Sep 17 00:00:00 2001 From: Zhijie Hou Date: Fri, 5 Dec 2025 17:53:50 +0800 Subject: [PATCH v2] Fix LOCK_TIMEOUT handling in slotsync worker. Previously, the slotsync worker used SIGINT to receive a graceful shutdown signal from the startup process on promotion. However, SIGINT is also used by the LOCK_TIMEOUT handler to trigger a query-cancel interrupt. Given that the slotsync worker can access and lock catalog tables while parsing libpq tuples, this overlapping use of SIGINT led to the slotsync worker ignoring LOCK_TIMEOUT signals and consequently waiting indefinitely on locks. This patch resolves this by replacing the current signal handler with the appropriate StatementCancelHandler for SIGINT within the slotsync worker. Furthermore, it updates the startup process to send a SIGUSR1 signal to notify slotsync of the need to stop during promotion. The slotsync worker now stops upon detecting that the shared memory flag (stopSignaled) is set to true. --- src/backend/replication/logical/slotsync.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/src/backend/replication/logical/slotsync.c b/src/backend/replication/logical/slotsync.c index 31d7cb3ca77..caabf158bbb 100644 --- a/src/backend/replication/logical/slotsync.c +++ b/src/backend/replication/logical/slotsync.c @@ -1254,10 +1254,10 @@ ProcessSlotSyncInterrupts(void) { CHECK_FOR_INTERRUPTS(); - if (ShutdownRequestPending) + if (SlotSyncCtx->stopSignaled) { ereport(LOG, - errmsg("replication slot synchronization worker is shutting down on receiving SIGINT")); + errmsg("replication slot synchronization worker will stop because promotion is triggered")); proc_exit(0); } @@ -1488,7 +1488,7 @@ ReplSlotSyncWorkerMain(const void *startup_data, size_t startup_data_len) /* Setup signal handling */ pqsignal(SIGHUP, SignalHandlerForConfigReload); - pqsignal(SIGINT, SignalHandlerForShutdownRequest); + pqsignal(SIGINT, StatementCancelHandler); pqsignal(SIGTERM, die); pqsignal(SIGFPE, FloatExceptionHandler); pqsignal(SIGUSR1, procsignal_sigusr1_handler); @@ -1595,7 +1595,8 @@ ReplSlotSyncWorkerMain(const void *startup_data, size_t startup_data_len) /* * The slot sync worker can't get here because it will only stop when it - * receives a SIGINT from the startup process, or when there is an error. + * receives a stop request from the startup process, or when there is an + * error. */ Assert(false); } @@ -1680,8 +1681,12 @@ ShutDownSlotSync(void) SpinLockRelease(&SlotSyncCtx->mutex); + /* + * Signal slotsync worker if it was still running. The worker will stop upon + * detecting that the stopSignaled flag is set to true. + */ if (worker_pid != InvalidPid) - kill(worker_pid, SIGINT); + kill(worker_pid, SIGUSR1); /* Wait for slot sync to end */ for (;;) -- 2.51.1.windows.1