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.

2 files changed, 33 insertions, 7 deletions

diff --git a/src/backend/postmaster/pgstat.c b/src/backend/postmaster/pgstat.c
index ac51d2bab7b..c971c06704a 100644
--- a/src/backend/postmaster/pgstat.c
+++ b/src/backend/postmaster/pgstat.c
@@ -13,7 +13,7 @@
  *
  *	Copyright (c) 2001-2006, PostgreSQL Global Development Group
  *
- *	$PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.135 2006/07/14 14:52:22 momjian Exp $
+ *	$PostgreSQL: pgsql/src/backend/postmaster/pgstat.c,v 1.136 2006/07/16 18:17:14 tgl Exp $
  * ----------
  */
 #include "postgres.h"
@@ -323,8 +323,12 @@ pgstat_init(void)
 		 * 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")));
@@ -375,8 +379,11 @@ 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")));
@@ -1533,17 +1540,23 @@ pgstat_setheader(PgStat_MsgHdr *hdr, StatMsgType mtype)
 static void
 pgstat_send(void *msg, int len)
 {
+	int			rc;
+
 	if (pgStatSock < 0)
 		return;
 
 	((PgStat_MsgHdr *) msg)->m_size = len;
 
+	/* 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
-	if (send(pgStatSock, msg, len, 0) < 0)
+	/* In debug builds, log send failures ... */
+	if (rc < 0)
 		elog(LOG, "could not send to statistics collector: %m");
-#else
-	send(pgStatSock, msg, len, 0);
-	/* We deliberately ignore any error from send() */
 #endif
 }
 
@@ -1718,9 +1731,13 @@ PgstatCollectorMain(int argc, char *argv[])
 			len = recv(pgStatSock, (char *) &msg,
 					   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 aa0f4e3418c..6c8cf982ce6 100644
--- 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 1.494 2006/07/15 15:47:17 tgl Exp $
+ *	  $PostgreSQL: pgsql/src/backend/postmaster/postmaster.c,v 1.495 2006/07/16 18:17:14 tgl Exp $
  *
  * NOTES
  *
@@ -1374,8 +1374,12 @@ 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")));
@@ -2524,6 +2528,7 @@ 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",
@@ -2534,7 +2539,11 @@ 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);
 }