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 ef826918995a31e43fabd7a723838e2f376a4d85..765ee1fe203e59084b9cb61d2747a11407fc720a 100644 (file)
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -13,7 +13,7 @@
  *
  *     Copyright (c) 2001-2005, PostgreSQL Global Development Group
  *
- *     $PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.87.4.2 2005/03/31 23:21:09 tgl Exp $
+ *     $PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.87.4.3 2006/07/16 18:17:35 tgl Exp $
  * ----------
  */
 #include "postgres.h"
@@ -337,8 +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")));
@@ -389,8 +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")));
@@ -1329,13 +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
 }
 
 
@@ -1863,9 +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 0cf734fff725a4b841f2c7e9a2564a8b9b04f16b..69a2b5bbcf7757f896924031208565c97978cbd0 100644 (file)
--- a/src/backend/postmaster/postmaster.c
+++ b/src/backend/postmaster/postmaster.c
@@ -37,7 +37,7 @@
  *
  *
  * IDENTIFICATION
- *       $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.443.4.7 2006/03/18 22:10:14 neilc Exp $
+ *       $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.443.4.8 2006/07/16 18:17:35 tgl Exp $
  *
  * NOTES
  *
@@ -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);
 }