Ensure that we retry rather than erroring out when send() or recv() return

EINTR; the stats code was failing to do this and so were a couple of places
in the postmaster.  The stats code assumed that recv() could not return EINTR
if a preceding select() showed the socket to be read-ready, but this is
demonstrably false with our Windows implementation of recv(), and it may
not be the case on all Unix variants either.  I think this explains the
intermittent stats regression test failures we've been seeing, as well
as reports of stats collector instability under high load on Windows.

Backpatch as far as 8.0.

diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index 14f7ef2189696cfa54bfea34ab5191fda9ffaa0b..26c6cdc54215119817406b0f49baf9ecf9a13333 100644 (file)
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -160,6 +160,7 @@ NON_EXEC_STATIC void PgstatCollectorMain(int argc, char *argv[]);
 static void pgstat_recvbuffer(void);
 static void pgstat_exit(SIGNAL_ARGS);
 static void pgstat_die(SIGNAL_ARGS);
+static void pgstat_beshutdown_hook(int code, Datum arg);
 
 static int     pgstat_add_backend(PgStat_MsgHdr *msg);
 static void pgstat_sub_backend(int procpid);
@@ -336,8 +337,12 @@ pgstat_init(void)
                 * packet filtering rules prevent it).
                 */
                test_byte = TESTBYTEVAL;
+
+retry1:
                if (send(pgStatSock, &test_byte, 1, 0) != 1)
                {
+                       if (errno == EINTR)
+                               goto retry1;    /* if interrupted, just retry */
                        ereport(LOG,
                                        (errcode_for_socket_access(),
                                         errmsg("could not send test message on socket for statistics collector: %m")));
@@ -388,8 +393,11 @@ pgstat_init(void)
 
                test_byte++;                    /* just make sure variable is changed */
 
+retry2:
                if (recv(pgStatSock, &test_byte, 1, 0) != 1)
                {
+                       if (errno == EINTR)
+                               goto retry2;    /* if interrupted, just retry */
                        ereport(LOG,
                                        (errcode_for_socket_access(),
                                         errmsg("could not receive test message on socket for statistics collector: %m")));
@@ -422,7 +430,7 @@ pgstat_init(void)
         * messages will be discarded; backends won't block waiting to send
         * messages to the collector.
         */
-       if (!set_noblock(pgStatSock))
+       if (!pg_set_noblock(pgStatSock))
        {
                ereport(LOG,
                                (errcode_for_socket_access(),
@@ -670,6 +678,25 @@ pgstat_bestart(void)
 
        pgstat_setheader(&msg.m_hdr, PGSTAT_MTYPE_BESTART);
        pgstat_send(&msg, sizeof(msg));
+
+       /*
+        * Set up a process-exit hook to ensure we flush the last batch of
+        * statistics to the collector.
+        */
+       on_proc_exit(pgstat_beshutdown_hook, 0);
+}
+
+/*
+ * Flush any remaining statistics counts out to the collector at process
+ * exit.   Without this, operations triggered during backend exit (such as
+ * temp table deletions) won't be counted.  This is an on_proc_exit hook,
+ * not on_shmem_exit, so that everything interesting must have happened
+ * already.
+ */
+static void
+pgstat_beshutdown_hook(int code, Datum arg)
+{
+       pgstat_report_tabstat();
 }
 
 
@@ -1309,13 +1336,24 @@ pgstat_setheader(PgStat_MsgHdr *hdr, int mtype)
 static void
 pgstat_send(void *msg, int len)
 {
+       int                     rc;
+
        if (pgStatSock < 0)
                return;
 
        ((PgStat_MsgHdr *) msg)->m_size = len;
 
-       send(pgStatSock, msg, len, 0);
-       /* We deliberately ignore any error from send() */
+       /* We'll retry after EINTR, but ignore all other failures */
+       do
+       {
+               rc = send(pgStatSock, msg, len, 0);
+       } while (rc < 0 && errno == EINTR);
+
+#ifdef USE_ASSERT_CHECKING
+       /* In debug builds, log send failures ... */
+       if (rc < 0)
+               elog(LOG, "could not send to statistics collector: %m");
+#endif
 }
 
 
@@ -1766,7 +1804,7 @@ pgstat_recvbuffer(void)
         * Set the write pipe to nonblock mode, so that we cannot block when
         * the collector falls behind.
         */
-       if (!set_noblock(writePipe))
+       if (!pg_set_noblock(writePipe))
                ereport(ERROR,
                                (errcode_for_socket_access(),
                                 errmsg("could not set statistics collector pipe to nonblocking mode: %m")));
@@ -1843,9 +1881,13 @@ pgstat_recvbuffer(void)
                        len = recv(pgStatSock, (char *) &input_buffer,
                                           sizeof(PgStat_Msg), 0);
                        if (len < 0)
+                       {
+                               if (errno == EINTR)
+                                       continue;
                                ereport(ERROR,
                                                (errcode_for_socket_access(),
                                           errmsg("could not read statistics message: %m")));
+                       }
 
                        /*
                         * We ignore messages that are smaller than our common header

diff --git a/src/backend/postmaster/postmaster.c b/src/backend/postmaster/postmaster.c
index 9aac1f2fbc374629a3d5f081368f4f48643b85eb..ab45db3a64ae6175168f446b3a1ae74170485ebf 100644 (file)
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -1399,8 +1399,12 @@ ProcessStartupPacket(Port *port, bool SSLdone)
 #else
                SSLok = 'N';                    /* No support for SSL */
 #endif
+
+retry1:
                if (send(port->sock, &SSLok, 1, 0) != 1)
                {
+                       if (errno == EINTR)
+                               goto retry1;    /* if interrupted, just retry */
                        ereport(COMMERROR,
                                        (errcode_for_socket_access(),
                                 errmsg("failed to send SSL negotiation response: %m")));
@@ -2532,6 +2536,7 @@ static void
 report_fork_failure_to_client(Port *port, int errnum)
 {
        char            buffer[1000];
+       int                     rc;
 
        /* Format the error message packet (always V2 protocol) */
        snprintf(buffer, sizeof(buffer), "E%s%s\n",
@@ -2542,7 +2547,11 @@ report_fork_failure_to_client(Port *port, int errnum)
        if (!pg_set_noblock(port->sock))
                return;
 
-       send(port->sock, buffer, strlen(buffer) + 1, 0);
+       /* We'll retry after EINTR, but ignore all other failures */
+       do
+       {
+               rc = send(port->sock, buffer, strlen(buffer) + 1, 0);
+       } while (rc < 0 && errno == EINTR);
 }