Fix LOCK_TIMEOUT handling during parallel apply.

Previously, the parallel apply worker used SIGINT to receive a graceful
shutdown signal from the leader apply worker. However, SIGINT is also used
by the LOCK_TIMEOUT handler to trigger a query-cancel interrupt. This
overlap caused the parallel apply worker to miss LOCK_TIMEOUT signals,
leading to incorrect behavior during lock wait/contention.

This patch resolves the conflict by switching the graceful shutdown signal
from SIGINT to SIGUSR2.

Reported-by: Zane Duffield <[email protected]>
Diagnosed-by: Zhijie Hou <[email protected]>
Author: Hayato Kuroda <[email protected]>
Reviewed-by: Amit Kapila <[email protected]>
Backpatch-through: 16, where it was introduced
Discussion: https://postgr.es/m/CACMiCkXyC4au74kvE2g6Y=mCEF8X6r-Ne_ty4r7qWkUjRE4+oQ@mail.gmail.com

diff --git a/src/backend/postmaster/interrupt.c b/src/backend/postmaster/interrupt.c
index 0ae9bf906ec1847aa4f63fd946f82231e7c362bf..ba63b84dfc5356433a30a381d5adb17ae124e2bc 100644 (file)
--- a/src/backend/postmaster/interrupt.c
+++ b/src/backend/postmaster/interrupt.c
@@ -94,9 +94,8 @@ SignalHandlerForCrashExit(SIGNAL_ARGS)
  * shut down and exit.
  *
  * Typically, this handler would be used for SIGTERM, but some processes use
- * other signals. In particular, the checkpointer exits on SIGUSR2, and the WAL
- * writer and the logical replication parallel apply worker exits on either
- * SIGINT or SIGTERM.
+ * other signals. In particular, the checkpointer and parallel apply worker
+ * exit on SIGUSR2, and the WAL writer exits on either SIGINT or SIGTERM.
  *
  * ShutdownRequestPending should be checked at a convenient place within the
  * main loop, or else the main loop should call ProcessMainLoopInterrupts.

diff --git a/src/backend/replication/logical/applyparallelworker.c b/src/backend/replication/logical/applyparallelworker.c
index 31a92d1a24abdb35708ddb48ddacc5bebeb0dd56..33b7ec7f029c35c1ff31343d74f36ba64bd04d8e 100644 (file)
--- a/src/backend/replication/logical/applyparallelworker.c
+++ b/src/backend/replication/logical/applyparallelworker.c
@@ -870,10 +870,17 @@ ParallelApplyWorkerMain(Datum main_arg)
 
    InitializingApplyWorker = true;
 
-   /* Setup signal handling. */
+   /*
+    * Setup signal handling.
+    *
+    * Note: We intentionally used SIGUSR2 to trigger a graceful shutdown
+    * initiated by the leader apply worker. This helps to differentiate it
+    * from the case where we abort the current transaction and exit on
+    * receiving SIGTERM.
+    */
    pqsignal(SIGHUP, SignalHandlerForConfigReload);
-   pqsignal(SIGINT, SignalHandlerForShutdownRequest);
    pqsignal(SIGTERM, die);
+   pqsignal(SIGUSR2, SignalHandlerForShutdownRequest);
    BackgroundWorkerUnblockSignals();
 
    /*
@@ -972,9 +979,9 @@ ParallelApplyWorkerMain(Datum main_arg)
 
    /*
     * The parallel apply worker must not get here because the parallel apply
-    * worker will only stop when it receives a SIGTERM or SIGINT from the
-    * leader, or when there is an error. None of these cases will allow the
-    * code to reach here.
+    * worker will only stop when it receives a SIGTERM or SIGUSR2 from the
+    * leader, or SIGINT from itself, or when there is an error. None of these
+    * cases will allow the code to reach here.
     */
    Assert(false);
 }

diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c
index c900b6cf3b163ca7cdc47705b94cb1103099ab32..218cefe86e20e2b473bbf50fa58438b933a052e9 100644 (file)
--- a/src/backend/replication/logical/launcher.c
+++ b/src/backend/replication/logical/launcher.c
@@ -650,7 +650,7 @@ logicalrep_worker_stop(Oid subid, Oid relid)
 /*
  * Stop the given logical replication parallel apply worker.
  *
- * Node that the function sends SIGINT instead of SIGTERM to the parallel apply
+ * Node that the function sends SIGUSR2 instead of SIGTERM to the parallel apply
  * worker so that the worker exits cleanly.
  */
 void
@@ -688,7 +688,7 @@ logicalrep_pa_worker_stop(ParallelApplyWorkerInfo *winfo)
     * Only stop the worker if the generation matches and the worker is alive.
     */
    if (worker->generation == generation && worker->proc)
-       logicalrep_worker_stop_internal(worker, SIGINT);
+       logicalrep_worker_stop_internal(worker, SIGUSR2);
 
    LWLockRelease(LogicalRepWorkerLock);
 }