Don't trust signalfd() on illumos.

Since commit 6a2a70a02, we've used signalfd() to receive latch wakeups
when building with WAIT_USE_EPOLL (default for Linux and illumos), and
our traditional self-pipe when falling back to WAIT_USE_POLL (default
for other Unixes with neither epoll() nor kqueue()).

Unexplained hangs and kernel panics have been reported on illumos
systems, apparently linked to this use of signalfd(), leading illumos
users and build farm members to have to define WAIT_USE_POLL explicitly
as a work-around.  A bug report exists at
https://www.illumos.org/issues/13700 but no fix is available yet.

Let's provide a way for illumos users to go back to self-pipes with
epoll(), like releases before 14, and choose that by default.  No change
for Linux users.  To help with development/debugging, macros
WAIT_USE_{EPOLL,POLL} and WAIT_USE_{SIGNALFD,SELF_PIPE} can be defined
explicitly to override the defaults.

Back-patch to 14, where we started using signalfd().

Reported-by: Japin Li <japinli@hotmail.com>
Reported-by: Olaf Bohlen <olbohlen@eenfach.de> (off-list)
Reviewed-by: Japin Li <japinli@hotmail.com>
Discussion: https://postgr.es/m/MEYP282MB1669C8D88F0997354C2313C1B6CA9%40MEYP282MB1669.AUSP282.PROD.OUTLOOK.COM

diff --git a/src/backend/storage/ipc/latch.c b/src/backend/storage/ipc/latch.c
index 41d359d68ed7f931d3d36f778644f6518ca68635..eb3a569aae14fd8a300a1c7b50d098436835d875 100644 (file)
--- a/src/backend/storage/ipc/latch.c
+++ b/src/backend/storage/ipc/latch.c
@@ -72,7 +72,7 @@
 #if defined(WAIT_USE_EPOLL) || defined(WAIT_USE_POLL) || \
        defined(WAIT_USE_KQUEUE) || defined(WAIT_USE_WIN32)
 /* don't overwrite manual choice */
-#elif defined(HAVE_SYS_EPOLL_H) && defined(HAVE_SYS_SIGNALFD_H)
+#elif defined(HAVE_SYS_EPOLL_H)
 #define WAIT_USE_EPOLL
 #elif defined(HAVE_KQUEUE)
 #define WAIT_USE_KQUEUE
@@ -84,6 +84,22 @@
 #error "no wait set implementation available"
 #endif
 
+/*
+ * By default, we use a self-pipe with poll() and a signalfd with epoll(), if
+ * available.  We avoid signalfd on illumos for now based on problem reports.
+ * For testing the choice can also be manually specified.
+ */
+#if defined(WAIT_USE_POLL) || defined(WAIT_USE_EPOLL)
+#if defined(WAIT_USE_SELF_PIPE) || defined(WAIT_USE_SIGNALFD)
+/* don't overwrite manual choice */
+#elif defined(WAIT_USE_EPOLL) && defined(HAVE_SYS_SIGNALFD_H) && \
+       !defined(__illumos__)
+#define WAIT_USE_SIGNALFD
+#else
+#define WAIT_USE_SELF_PIPE
+#endif
+#endif
+
 /* typedef in latch.h */
 struct WaitEventSet
 {
@@ -146,12 +162,12 @@ static WaitEventSet *LatchWaitSet;
 static volatile sig_atomic_t waiting = false;
 #endif
 
-#ifdef WAIT_USE_EPOLL
+#ifdef WAIT_USE_SIGNALFD
 /* On Linux, we'll receive SIGURG via a signalfd file descriptor. */
 static int     signal_fd = -1;
 #endif
 
-#if defined(WAIT_USE_POLL)
+#ifdef WAIT_USE_SELF_PIPE
 /* Read and write ends of the self-pipe */
 static int     selfpipe_readfd = -1;
 static int     selfpipe_writefd = -1;
@@ -164,7 +180,7 @@ static void latch_sigurg_handler(SIGNAL_ARGS);
 static void sendSelfPipeByte(void);
 #endif
 
-#if defined(WAIT_USE_POLL) || defined(WAIT_USE_EPOLL)
+#if defined(WAIT_USE_SELF_PIPE) || defined(WAIT_USE_SIGNALFD)
 static void drain(void);
 #endif
 
@@ -190,7 +206,7 @@ static inline int WaitEventSetWaitBlock(WaitEventSet *set, int cur_timeout,
 void
 InitializeLatchSupport(void)
 {
-#if defined(WAIT_USE_POLL)
+#if defined(WAIT_USE_SELF_PIPE)
        int                     pipefd[2];
 
        if (IsUnderPostmaster)
@@ -264,7 +280,7 @@ InitializeLatchSupport(void)
        pqsignal(SIGURG, latch_sigurg_handler);
 #endif
 
-#ifdef WAIT_USE_EPOLL
+#ifdef WAIT_USE_SIGNALFD
        sigset_t        signalfd_mask;
 
        /* Block SIGURG, because we'll receive it through a signalfd. */
@@ -316,7 +332,7 @@ ShutdownLatchSupport(void)
                LatchWaitSet = NULL;
        }
 
-#if defined(WAIT_USE_POLL)
+#if defined(WAIT_USE_SELF_PIPE)
        close(selfpipe_readfd);
        close(selfpipe_writefd);
        selfpipe_readfd = -1;
@@ -324,7 +340,7 @@ ShutdownLatchSupport(void)
        selfpipe_owner_pid = InvalidPid;
 #endif
 
-#if defined(WAIT_USE_EPOLL)
+#if defined(WAIT_USE_SIGNALFD)
        close(signal_fd);
        signal_fd = -1;
 #endif
@@ -341,9 +357,12 @@ InitLatch(Latch *latch)
        latch->owner_pid = MyProcPid;
        latch->is_shared = false;
 
-#if defined(WAIT_USE_POLL)
+#if defined(WAIT_USE_SELF_PIPE)
        /* Assert InitializeLatchSupport has been called in this process */
        Assert(selfpipe_readfd >= 0 && selfpipe_owner_pid == MyProcPid);
+#elif defined(WAIT_USE_SIGNALFD)
+       /* Assert InitializeLatchSupport has been called in this process */
+       Assert(signal_fd >= 0);
 #elif defined(WAIT_USE_WIN32)
        latch->event = CreateEvent(NULL, TRUE, FALSE, NULL);
        if (latch->event == NULL)
@@ -407,9 +426,12 @@ OwnLatch(Latch *latch)
        /* Sanity checks */
        Assert(latch->is_shared);
 
-#if defined(WAIT_USE_POLL)
+#if defined(WAIT_USE_SELF_PIPE)
        /* Assert InitializeLatchSupport has been called in this process */
        Assert(selfpipe_readfd >= 0 && selfpipe_owner_pid == MyProcPid);
+#elif defined(WAIT_USE_SIGNALFD)
+       /* Assert InitializeLatchSupport has been called in this process */
+       Assert(signal_fd >= 0);
 #endif
 
        owner_pid = latch->owner_pid;
@@ -620,7 +642,7 @@ SetLatch(Latch *latch)
                return;
        else if (owner_pid == MyProcPid)
        {
-#if defined(WAIT_USE_POLL)
+#if defined(WAIT_USE_SELF_PIPE)
                if (waiting)
                        sendSelfPipeByte();
 #else
@@ -907,9 +929,9 @@ AddWaitEventToSet(WaitEventSet *set, uint32 events, pgsocket fd, Latch *latch,
        {
                set->latch = latch;
                set->latch_pos = event->pos;
-#if defined(WAIT_USE_POLL)
+#if defined(WAIT_USE_SELF_PIPE)
                event->fd = selfpipe_readfd;
-#elif defined(WAIT_USE_EPOLL)
+#elif defined(WAIT_USE_SIGNALFD)
                event->fd = signal_fd;
 #else
                event->fd = PGINVALID_SOCKET;
@@ -2086,7 +2108,7 @@ GetNumRegisteredWaitEvents(WaitEventSet *set)
        return set->nevents;
 }
 
-#if defined(WAIT_USE_POLL)
+#if defined(WAIT_USE_SELF_PIPE)
 
 /*
  * SetLatch uses SIGURG to wake up the process waiting on the latch.
@@ -2137,7 +2159,7 @@ retry:
 
 #endif
 
-#if defined(WAIT_USE_POLL) || defined(WAIT_USE_EPOLL)
+#if defined(WAIT_USE_SELF_PIPE) || defined(WAIT_USE_SIGNALFD)
 
 /*
  * Read all available data from self-pipe or signalfd.
@@ -2153,7 +2175,7 @@ drain(void)
        int                     rc;
        int                     fd;
 
-#ifdef WAIT_USE_POLL
+#ifdef WAIT_USE_SELF_PIPE
        fd = selfpipe_readfd;
 #else
        fd = signal_fd;
@@ -2171,7 +2193,7 @@ drain(void)
                        else
                        {
                                waiting = false;
-#ifdef WAIT_USE_POLL
+#ifdef WAIT_USE_SELF_PIPE
                                elog(ERROR, "read() on self-pipe failed: %m");
 #else
                                elog(ERROR, "read() on signalfd failed: %m");
@@ -2181,7 +2203,7 @@ drain(void)
                else if (rc == 0)
                {
                        waiting = false;
-#ifdef WAIT_USE_POLL
+#ifdef WAIT_USE_SELF_PIPE
                        elog(ERROR, "unexpected EOF on self-pipe");
 #else
                        elog(ERROR, "unexpected EOF on signalfd");