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

6 files changed, 40 insertions, 61 deletions

diff --git a/src/backend/postmaster/autovacuum.c b/src/backend/postmaster/autovacuum.c
index 31e98db9d69..2d5086d4062 100644
--- a/src/backend/postmaster/autovacuum.c
+++ b/src/backend/postmaster/autovacuum.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;
diff --git a/src/backend/postmaster/bgwriter.c b/src/backend/postmaster/bgwriter.c
index 54a042843da..bd8dc61182d 100644
--- a/src/backend/postmaster/bgwriter.c
+++ b/src/backend/postmaster/bgwriter.c
@@ -335,7 +335,7 @@ BackgroundWriterMain(void)
 		 * normal operation.
 		 */
 		rc = WaitLatch(MyLatch,
-					   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
+					   WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
 					   BgWriterDelay /* ms */ , WAIT_EVENT_BGWRITER_MAIN);
 
 		/*
@@ -362,20 +362,13 @@ BackgroundWriterMain(void)
 			StrategyNotifyBgWriter(MyProc->pgprocno);
 			/* Sleep ... */
 			rc = WaitLatch(MyLatch,
-						   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
+						   WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
 						   BgWriterDelay * HIBERNATE_FACTOR,
 						   WAIT_EVENT_BGWRITER_HIBERNATE);
 			/* Reset the notification request in case we timed out */
 			StrategyNotifyBgWriter(-1);
 		}
 
-		/*
-		 * Emergency bailout if postmaster has died.  This is to avoid the
-		 * necessity for manual cleanup of all postmaster children.
-		 */
-		if (rc & WL_POSTMASTER_DEATH)
-			exit(1);
-
 		prev_hibernate = can_hibernate;
 	}
 }
diff --git a/src/backend/postmaster/checkpointer.c b/src/backend/postmaster/checkpointer.c
index 9eac86b554b..b9c118e1560 100644
--- a/src/backend/postmaster/checkpointer.c
+++ b/src/backend/postmaster/checkpointer.c
@@ -340,7 +340,6 @@ CheckpointerMain(void)
 		pg_time_t	now;
 		int			elapsed_secs;
 		int			cur_timeout;
-		int			rc;
 
 		/* Clear any already-pending wakeups */
 		ResetLatch(MyLatch);
@@ -541,17 +540,10 @@ CheckpointerMain(void)
 			cur_timeout = Min(cur_timeout, XLogArchiveTimeout - elapsed_secs);
 		}
 
-		rc = WaitLatch(MyLatch,
-					   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
-					   cur_timeout * 1000L /* convert to ms */ ,
-					   WAIT_EVENT_CHECKPOINTER_MAIN);
-
-		/*
-		 * Emergency bailout if postmaster has died.  This is to avoid the
-		 * necessity for manual cleanup of all postmaster children.
-		 */
-		if (rc & WL_POSTMASTER_DEATH)
-			exit(1);
+		(void) WaitLatch(MyLatch,
+						 WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+						 cur_timeout * 1000L /* convert to ms */ ,
+						 WAIT_EVENT_CHECKPOINTER_MAIN);
 	}
 }
 
diff --git a/src/backend/postmaster/pgarch.c b/src/backend/postmaster/pgarch.c
index 0ebd63650c6..844b9d1b0e9 100644
--- a/src/backend/postmaster/pgarch.c
+++ b/src/backend/postmaster/pgarch.c
@@ -390,6 +390,8 @@ pgarch_MainLoop(void)
 							   WAIT_EVENT_ARCHIVER_MAIN);
 				if (rc & WL_TIMEOUT)
 					wakened = true;
+				if (rc & WL_POSTMASTER_DEATH)
+					time_to_stop = true;
 			}
 			else
 				wakened = true;
@@ -400,7 +402,7 @@ pgarch_MainLoop(void)
 		 * or after completing one more archiving cycle after receiving
 		 * SIGUSR2.
 		 */
-	} while (PostmasterIsAlive() && !time_to_stop);
+	} while (!time_to_stop);
 }
 
 /*
diff --git a/src/backend/postmaster/syslogger.c b/src/backend/postmaster/syslogger.c
index 35755138890..fbeee311092 100644
--- a/src/backend/postmaster/syslogger.c
+++ b/src/backend/postmaster/syslogger.c
@@ -168,6 +168,7 @@ SysLoggerMain(int argc, char *argv[])
 	char	   *currentLogFilename;
 	int			currentLogRotationAge;
 	pg_time_t	now;
+	WaitEventSet *wes;
 
 	now = MyStartTime;
 
@@ -294,13 +295,29 @@ SysLoggerMain(int argc, char *argv[])
 	 */
 	whereToSendOutput = DestNone;
 
+	/*
+	 * Set up a reusable WaitEventSet object we'll use to wait for our latch,
+	 * and (except on Windows) our socket.
+	 *
+	 * Unlike all other postmaster child processes, we'll ignore postmaster
+	 * death because we want to collect final log output from all backends and
+	 * then exit last.  We'll do that by running until we see EOF on the
+	 * syslog pipe, which implies that all other backends have exited
+	 * (including the postmaster).
+	 */
+	wes = CreateWaitEventSet(CurrentMemoryContext, 2);
+	AddWaitEventToSet(wes, WL_LATCH_SET, PGINVALID_SOCKET, MyLatch, NULL);
+#ifndef WIN32
+	AddWaitEventToSet(wes, WL_SOCKET_READABLE, syslogPipe[0], NULL, NULL);
+#endif
+
 	/* main worker loop */
 	for (;;)
 	{
 		bool		time_based_rotation = false;
 		int			size_rotation_for = 0;
 		long		cur_timeout;
-		int			cur_flags;
+		WaitEvent	event;
 
 #ifndef WIN32
 		int			rc;
@@ -436,25 +453,18 @@ SysLoggerMain(int argc, char *argv[])
 			}
 			else
 				cur_timeout = 0;
-			cur_flags = WL_TIMEOUT;
 		}
 		else
-		{
 			cur_timeout = -1L;
-			cur_flags = 0;
-		}
 
 		/*
 		 * Sleep until there's something to do
 		 */
 #ifndef WIN32
-		rc = WaitLatchOrSocket(MyLatch,
-							   WL_LATCH_SET | WL_SOCKET_READABLE | cur_flags,
-							   syslogPipe[0],
-							   cur_timeout,
-							   WAIT_EVENT_SYSLOGGER_MAIN);
+		rc = WaitEventSetWait(wes, cur_timeout, &event, 1,
+							  WAIT_EVENT_SYSLOGGER_MAIN);
 
-		if (rc & WL_SOCKET_READABLE)
+		if (rc == 1 && event.events == WL_SOCKET_READABLE)
 		{
 			int			bytesRead;
 
@@ -501,10 +511,8 @@ SysLoggerMain(int argc, char *argv[])
 		 */
 		LeaveCriticalSection(&sysloggerSection);
 
-		(void) WaitLatch(MyLatch,
-						 WL_LATCH_SET | cur_flags,
-						 cur_timeout,
-						 WAIT_EVENT_SYSLOGGER_MAIN);
+		(void) WaitEventSetWait(wes, cur_timeout, &event, 1,
+								WAIT_EVENT_SYSLOGGER_MAIN);
 
 		EnterCriticalSection(&sysloggerSection);
 #endif							/* WIN32 */
diff --git a/src/backend/postmaster/walwriter.c b/src/backend/postmaster/walwriter.c
index 3e09827854d..0ae733e886a 100644
--- a/src/backend/postmaster/walwriter.c
+++ b/src/backend/postmaster/walwriter.c
@@ -223,7 +223,6 @@ WalWriterMain(void)
 	for (;;)
 	{
 		long		cur_timeout;
-		int			rc;
 
 		/*
 		 * Advertise whether we might hibernate in this cycle.  We do this
@@ -276,17 +275,10 @@ WalWriterMain(void)
 		else
 			cur_timeout = WalWriterDelay * HIBERNATE_FACTOR;
 
-		rc = WaitLatch(MyLatch,
-					   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
-					   cur_timeout,
-					   WAIT_EVENT_WAL_WRITER_MAIN);
-
-		/*
-		 * Emergency bailout if postmaster has died.  This is to avoid the
-		 * necessity for manual cleanup of all postmaster children.
-		 */
-		if (rc & WL_POSTMASTER_DEATH)
-			exit(1);
+		(void) WaitLatch(MyLatch,
+						 WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
+						 cur_timeout,
+						 WAIT_EVENT_WAL_WRITER_MAIN);
 	}
 }