Introduce WaitEventSet API.

Commit ac1d794 ("Make idle backends exit if the postmaster dies.")
introduced a regression on, at least, large linux systems. Constantly
adding the same postmaster_alive_fds to the OSs internal datastructures
for implementing poll/select can cause significant contention; leading
to a performance regression of nearly 3x in one example.

This can be avoided by using e.g. linux' epoll, which avoids having to
add/remove file descriptors to the wait datastructures at a high rate.
Unfortunately the current latch interface makes it hard to allocate any
persistent per-backend resources.

Replace, with a backward compatibility layer, WaitLatchOrSocket with a
new WaitEventSet API. Users can allocate such a Set across multiple
calls, and add more than one file-descriptor to wait on. The latter has
been added because there's upcoming postgres features where that will be
helpful.

In addition to the previously existing poll(2), select(2),
WaitForMultipleObjects() implementations also provide an epoll_wait(2)
based implementation to address the aforementioned performance
problem. Epoll is only available on linux, but that is the most likely
OS for machines large enough (four sockets) to reproduce the problem.

To actually address the aforementioned regression, create and use a
long-lived WaitEventSet for FE/BE communication.  There are additional
places that would benefit from a long-lived set, but that's a task for
another day.

Thanks to Amit Kapila, who helped make the windows code I blindly wrote
actually work.

Reported-By: Dmitry Vasilyev Discussion:
CAB-SwXZh44_2ybvS5Z67p_CDz=XFn4hNAD=CnMEF+QqkXwFrGg@mail.gmail.com
[email protected]

Author: anarazel

configure

@@ -10193,7 +10193,7 @@ fi
 ## Header files
 ##
 
-for ac_header in atomic.h crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h mbarrier.h poll.h pwd.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h
+for ac_header in atomic.h crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h mbarrier.h poll.h pwd.h sys/epoll.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h
 do :
   as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
 ac_fn_c_check_header_mongrel "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default"

configure.in

@@ -1183,7 +1183,7 @@ AC_SUBST(UUID_LIBS)
 ##
 
 dnl sys/socket.h is required by AC_FUNC_ACCEPT_ARGTYPES
-AC_CHECK_HEADERS([atomic.h crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h mbarrier.h poll.h pwd.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h])
+AC_CHECK_HEADERS([atomic.h crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h mbarrier.h poll.h pwd.h sys/epoll.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h])
 
 # On BSD, test for net/if.h will fail unless sys/socket.h
 # is included first.

src/backend/libpq/be-secure.c

@@ -140,13 +140,13 @@ secure_read(Port *port, void *ptr, size_t len)
 	/* In blocking mode, wait until the socket is ready */
 	if (n < 0 && !port->noblock && (errno == EWOULDBLOCK || errno == EAGAIN))
 	{
-		int			w;
+		WaitEvent   event;
 
 		Assert(waitfor);
 
-		w = WaitLatchOrSocket(MyLatch,
-							  WL_LATCH_SET | WL_POSTMASTER_DEATH | waitfor,
-							  port->sock, 0);
+		ModifyWaitEvent(FeBeWaitSet, 0, waitfor, NULL);
+
+		WaitEventSetWait(FeBeWaitSet, -1 /* no timeout */, &event, 1);
 
 		/*
 		 * If the postmaster has died, it's not safe to continue running,
@@ -165,13 +165,13 @@ secure_read(Port *port, void *ptr, size_t len)
 		 * cycles checking for this very rare condition, and this should cause
 		 * us to exit quickly in most cases.)
 		 */
-		if (w & WL_POSTMASTER_DEATH)
+		if (event.events & WL_POSTMASTER_DEATH)
 			ereport(FATAL,
 					(errcode(ERRCODE_ADMIN_SHUTDOWN),
 					errmsg("terminating connection due to unexpected postmaster exit")));
 
 		/* Handle interrupt. */
-		if (w & WL_LATCH_SET)
+		if (event.events & WL_LATCH_SET)
 		{
 			ResetLatch(MyLatch);
 			ProcessClientReadInterrupt(true);
@@ -241,22 +241,22 @@ secure_write(Port *port, void *ptr, size_t len)
 
 	if (n < 0 && !port->noblock && (errno == EWOULDBLOCK || errno == EAGAIN))
 	{
-		int			w;
+		WaitEvent   event;
 
 		Assert(waitfor);
 
-		w = WaitLatchOrSocket(MyLatch,
-							  WL_LATCH_SET | WL_POSTMASTER_DEATH | waitfor,
-							  port->sock, 0);
+		ModifyWaitEvent(FeBeWaitSet, 0, waitfor, NULL);
+
+		WaitEventSetWait(FeBeWaitSet, -1 /* no timeout */, &event, 1);
 
 		/* See comments in secure_read. */
-		if (w & WL_POSTMASTER_DEATH)
+		if (event.events & WL_POSTMASTER_DEATH)
 			ereport(FATAL,
 					(errcode(ERRCODE_ADMIN_SHUTDOWN),
 					errmsg("terminating connection due to unexpected postmaster exit")));
 
 		/* Handle interrupt. */
-		if (w & WL_LATCH_SET)
+		if (event.events & WL_LATCH_SET)
 		{
 			ResetLatch(MyLatch);
 			ProcessClientWriteInterrupt(true);

src/backend/libpq/pqcomm.c

@@ -201,6 +201,11 @@ pq_init(void)
 				(errmsg("could not set socket to nonblocking mode: %m")));
 #endif
 
+	FeBeWaitSet = CreateWaitEventSet(TopMemoryContext, 3);
+	AddWaitEventToSet(FeBeWaitSet, WL_SOCKET_WRITEABLE, MyProcPort->sock,
+					  NULL, NULL);
+	AddWaitEventToSet(FeBeWaitSet, WL_LATCH_SET, -1, MyLatch, NULL);
+	AddWaitEventToSet(FeBeWaitSet, WL_POSTMASTER_DEATH, -1, NULL, NULL);
 }
 
 /* --------------------------------