Add WL_EXIT_ON_PM_DEATH pseudo-event.

Users of the WaitEventSet and WaitLatch() APIs can now choose between
asking for WL_POSTMASTER_DEATH and then handling it explicitly, or asking
for WL_EXIT_ON_PM_DEATH to trigger immediate exit on postmaster death.
This reduces code duplication, since almost all callers want the latter.

Repair all code that was previously ignoring postmaster death completely,
or requesting the event but ignoring it, or requesting the event but then
doing an unconditional PostmasterIsAlive() call every time through its
event loop (which is an expensive syscall on platforms for which we don't
have USE_POSTMASTER_DEATH_SIGNAL support).

Assert that callers of WaitLatchXXX() under the postmaster remember to
ask for either WL_POSTMASTER_DEATH or WL_EXIT_ON_PM_DEATH, to prevent
future bugs.

The only process that doesn't handle postmaster death is syslogger.  It
waits until all backends holding the write end of the syslog pipe
(including the postmaster) have closed it by exiting, to be sure to
capture any parting messages.  By using the WaitEventSet API directly
it avoids the new assertion, and as a by-product it may be slightly
more efficient on platforms that have epoll().

Author: Thomas Munro
Reviewed-by: Kyotaro Horiguchi, Heikki Linnakangas, Tom Lane
Discussion: https://postgr.es/m/CAEepm%3D1TCviRykkUb69ppWLr_V697rzd1j3eZsRMmbXvETfqbQ%40mail.gmail.com,
            https://postgr.es/m/CAEepm=2LqHzizbe7muD7-2yHUbTOoF7Q+qkSD5Q41kuhttRTwA@mail.gmail.com

Author: macdice

-

@@ -220,7 +220,7 @@ autoprewarm_main(Datum main_arg)
 		{
 			/* We're only dumping at shutdown, so just wait forever. */
 			rc = WaitLatch(&MyProc->procLatch,
-						   WL_LATCH_SET | WL_POSTMASTER_DEATH,
+						   WL_LATCH_SET | WL_EXIT_ON_PM_DEATH,
 						   -1L,
 						   PG_WAIT_EXTENSION);
 		}
@@ -249,15 +249,13 @@ autoprewarm_main(Datum main_arg)
 
 			/* Sleep until the next dump time. */
 			rc = WaitLatch(&MyProc->procLatch,
-						   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
+						   WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
 						   delay_in_ms,
 						   PG_WAIT_EXTENSION);
 		}
 
-		/* Reset the latch, bail out if postmaster died, otherwise loop. */
+		/* Reset the latch, loop. */
 		ResetLatch(&MyProc->procLatch);
-		if (rc & WL_POSTMASTER_DEATH)
-			proc_exit(1);
 	}
 
 	/*

contrib/pg_prewarm/autoprewarm.c

@@ -546,7 +546,8 @@ pgfdw_get_result(PGconn *conn, const char *query)
 
 				/* Sleep until there's something to do */
 				wc = WaitLatchOrSocket(MyLatch,
-									   WL_LATCH_SET | WL_SOCKET_READABLE,
+									   WL_LATCH_SET | WL_SOCKET_READABLE |
+									   WL_EXIT_ON_PM_DEATH,
 									   PQsocket(conn),
 									   -1L, PG_WAIT_EXTENSION);
 				ResetLatch(MyLatch);
@@ -1152,7 +1153,8 @@ pgfdw_get_cleanup_result(PGconn *conn, TimestampTz endtime, PGresult **result)
 
 				/* Sleep until there's something to do */
 				wc = WaitLatchOrSocket(MyLatch,
-									   WL_LATCH_SET | WL_SOCKET_READABLE | WL_TIMEOUT,
+									   WL_LATCH_SET | WL_SOCKET_READABLE |
+									   WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
 									   PQsocket(conn),
 									   cur_timeout, PG_WAIT_EXTENSION);
 				ResetLatch(MyLatch);

contrib/postgres_fdw/connection.c

@@ -692,13 +692,9 @@ WaitForParallelWorkersToAttach(ParallelContext *pcxt)
 				 * just end up waiting for the same worker again.
 				 */
 				rc = WaitLatch(MyLatch,
-							   WL_LATCH_SET | WL_POSTMASTER_DEATH,
+							   WL_LATCH_SET | WL_EXIT_ON_PM_DEATH,
 							   -1, WAIT_EVENT_BGWORKER_STARTUP);
 
-				/* emergency bailout if postmaster has died */
-				if (rc & WL_POSTMASTER_DEATH)
-					proc_exit(1);
-
 				if (rc & WL_LATCH_SET)
 					ResetLatch(MyLatch);
 			}
@@ -815,8 +811,8 @@ WaitForParallelWorkersToFinish(ParallelContext *pcxt)
 			}
 		}
 
-		WaitLatch(MyLatch, WL_LATCH_SET, -1,
-				  WAIT_EVENT_PARALLEL_FINISH);
+		(void) WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH, -1,
+						 WAIT_EVENT_PARALLEL_FINISH);
 		ResetLatch(MyLatch);
 	}
 

src/backend/access/transam/parallel.c

@@ -6189,10 +6189,10 @@ recoveryApplyDelay(XLogReaderState *record)
 		elog(DEBUG2, "recovery apply delay %ld seconds, %d milliseconds",
 			 secs, microsecs / 1000);
 
-		WaitLatch(&XLogCtl->recoveryWakeupLatch,
-				  WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
-				  secs * 1000L + microsecs / 1000,
-				  WAIT_EVENT_RECOVERY_APPLY_DELAY);
+		(void) WaitLatch(&XLogCtl->recoveryWakeupLatch,
+						 WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+						 secs * 1000L + microsecs / 1000,
+						 WAIT_EVENT_RECOVERY_APPLY_DELAY);
 	}
 	return true;
 }
@@ -12093,9 +12093,11 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
 						wait_time = wal_retrieve_retry_interval -
 							(secs * 1000 + usecs / 1000);
 
-						WaitLatch(&XLogCtl->recoveryWakeupLatch,
-								  WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
-								  wait_time, WAIT_EVENT_RECOVERY_WAL_STREAM);
+						(void) WaitLatch(&XLogCtl->recoveryWakeupLatch,
+										 WL_LATCH_SET | WL_TIMEOUT |
+										 WL_EXIT_ON_PM_DEATH,
+										 wait_time,
+										 WAIT_EVENT_RECOVERY_WAL_STREAM);
 						ResetLatch(&XLogCtl->recoveryWakeupLatch);
 						now = GetCurrentTimestamp();
 					}
@@ -12269,9 +12271,10 @@ WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
 					 * Wait for more WAL to arrive. Time out after 5 seconds
 					 * to react to a trigger file promptly.
 					 */
-					WaitLatch(&XLogCtl->recoveryWakeupLatch,
-							  WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
-							  5000L, WAIT_EVENT_RECOVERY_WAL_ALL);
+					(void) WaitLatch(&XLogCtl->recoveryWakeupLatch,
+									 WL_LATCH_SET | WL_TIMEOUT |
+									 WL_EXIT_ON_PM_DEATH,
+									 5000L, WAIT_EVENT_RECOVERY_WAL_ALL);
 					ResetLatch(&XLogCtl->recoveryWakeupLatch);
 					break;
 				}

src/backend/access/transam/xlog.c

@@ -764,10 +764,10 @@ pg_promote(PG_FUNCTION_ARGS)
 
 		CHECK_FOR_INTERRUPTS();
 
-		WaitLatch(MyLatch,
-				  WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
-				  1000L / WAITS_PER_SECOND,
-				  WAIT_EVENT_PROMOTE);
+		(void) WaitLatch(MyLatch,
+						 WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
+						 1000L / WAITS_PER_SECOND,
+						 WAIT_EVENT_PROMOTE);
 	}
 
 	ereport(WARNING,

src/backend/access/transam/xlogfuncs.c

@@ -383,7 +383,8 @@ gather_readnext(GatherState *gatherstate)
 				return NULL;
 
 			/* Nothing to do except wait for developments. */
-			WaitLatch(MyLatch, WL_LATCH_SET, 0, WAIT_EVENT_EXECUTE_GATHER);
+			(void) WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH, 0,
+							 WAIT_EVENT_EXECUTE_GATHER);
 			ResetLatch(MyLatch);
 			nvisited = 0;
 		}

src/backend/executor/nodeGather.c

@@ -410,8 +410,8 @@ be_tls_open_server(Port *port)
 				else
 					waitfor = WL_SOCKET_WRITEABLE;
 
-				WaitLatchOrSocket(MyLatch, waitfor, port->sock, 0,
-								  WAIT_EVENT_SSL_OPEN_SERVER);
+				(void) WaitLatchOrSocket(MyLatch, waitfor, port->sock, 0,
+										 WAIT_EVENT_SSL_OPEN_SERVER);
 				goto aloop;
 			case SSL_ERROR_SYSCALL:
 				if (r < 0)

src/backend/libpq/be-secure-openssl.c

@@ -168,8 +168,8 @@ mq_putmessage(char msgtype, const char *s, size_t len)
 		if (result != SHM_MQ_WOULD_BLOCK)
 			break;
 
-		WaitLatch(MyLatch, WL_LATCH_SET, 0,
-				  WAIT_EVENT_MQ_PUT_MESSAGE);
+		(void) WaitLatch(MyLatch, WL_LATCH_SET | WL_EXIT_ON_PM_DEATH, 0,
+						 WAIT_EVENT_MQ_PUT_MESSAGE);
 		ResetLatch(MyLatch);
 		CHECK_FOR_INTERRUPTS();
 	}

src/backend/libpq/pqmq.c

@@ -628,7 +628,6 @@ AutoVacLauncherMain(int argc, char *argv[])
 		struct timeval nap;
 		TimestampTz current_time = 0;
 		bool		can_launch;
-		int			rc;
 
 		/*
 		 * This loop is a bit different from the normal use of WaitLatch,
@@ -644,23 +643,16 @@ AutoVacLauncherMain(int argc, char *argv[])
 		 * Wait until naptime expires or we get some type of signal (all the
 		 * signal handlers will wake us by calling SetLatch).
 		 */
-		rc = WaitLatch(MyLatch,
-					   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
-					   (nap.tv_sec * 1000L) + (nap.tv_usec / 1000L),
-					   WAIT_EVENT_AUTOVACUUM_MAIN);
+		(void) WaitLatch(MyLatch,
+						 WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+						 (nap.tv_sec * 1000L) + (nap.tv_usec / 1000L),
+						 WAIT_EVENT_AUTOVACUUM_MAIN);
 
 		ResetLatch(MyLatch);
 
 		/* Process sinval catchup interrupts that happened while sleeping */
 		ProcessCatchupInterrupt();
 
-		/*
-		 * Emergency bailout if postmaster has died.  This is to avoid the
-		 * necessity for manual cleanup of all postmaster children.
-		 */
-		if (rc & WL_POSTMASTER_DEATH)
-			proc_exit(1);
-
 		/* the normal shutdown case */
 		if (got_SIGTERM)
 			break;