Fix bug in heartbeat.

Following error message was recorded every wd_heartbeat_deadtime since
65dbbe7a0 was committed.

2025-02-10 10:50:37.990: heart_beat_receiver pid 1060625: ERROR:  failed to get socket data from heartbeat receive socket list
2025-02-10 10:50:37.990: heart_beat_receiver pid 1060625: DETAIL:  select() got timeout, exceed 30 sec(s)

The heartbeat receiver waits for heartbeart packet arrives in
select(2) until wd_heartbeat_deadtime is expired. I believe the logic
is wrong: it should wait forever until the packet arrives. In v4.5 or
earlier, the hearbeart receiver waits in recvfrom() without
timeout. So give NULL to select's timeout parameter so that it waits
forever.  Since 65dbbe7a0 is only in master branch, no backpatch is
made.

Reported by: Peng Bo

diff --git a/src/watchdog/wd_heartbeat.c b/src/watchdog/wd_heartbeat.c
index 67dcf505d645a1844c66acd4ca732dfcf63aecec..8568a1b948afe642064ac3a12dd7accadbb92e68 100644 (file)
--- a/src/watchdog/wd_heartbeat.c
+++ b/src/watchdog/wd_heartbeat.c
@@ -6,7 +6,7 @@
  * pgpool: a language independent connection pool server for PostgreSQL
  * written by Tatsuo Ishii
  *
- * Copyright (c) 2003-2020     PgPool Global Development Group
+ * Copyright (c) 2003-2025     PgPool Global Development Group
  *
  * Permission to use, copy, modify, and distribute this software and
  * its documentation for any purpose and without fee is hereby
@@ -75,7 +75,7 @@ static int    hton_wd_hb_packet(WdHbPacket * to, WdHbPacket * from);
 static int     ntoh_wd_hb_packet(WdHbPacket * to, WdHbPacket * from);
 static int     packet_to_string_hb(WdHbPacket * pkt, char *str, int maxlen);
 static void wd_set_reuseport(int sock);
-static int     select_socket_from_list(List *socks, int timeout_sec);
+static int     select_socket_from_list(List *socks);
 
 static int     wd_create_hb_send_socket(WdHbIf * hb_if);
 static List *wd_create_hb_recv_socket(WdHbIf * hb_if);
@@ -87,7 +87,7 @@ static void wd_hb_recv(int sock, WdHbPacket * pkt, char *from_addr);
   * Readable socket will be returned among the listening socket list.
   */
 static int
-select_socket_from_list(List *socks, int timeout_sec)
+select_socket_from_list(List *socks)
 {
        int                     select_ret;
        int                     maxsfd = 0;
@@ -95,10 +95,6 @@ select_socket_from_list(List *socks, int timeout_sec)
        fd_set          rfds;
        fd_set          efds;
        ListCell   *lc;
-       struct timeval tv;
-
-       tv.tv_sec = timeout_sec;
-       tv.tv_usec = 0;
 
        FD_ZERO(&rfds);
        FD_ZERO(&efds);
@@ -112,7 +108,10 @@ select_socket_from_list(List *socks, int timeout_sec)
                        maxsfd = sock;
        }
 
-       select_ret = select(maxsfd + 1, &rfds, NULL, &efds, &tv);
+       /*
+        * select(2) blocks here until some packets arrive.
+        */
+       select_ret = select(maxsfd + 1, &rfds, NULL, &efds, NULL);
 
        if (select_ret > 0)
        {
@@ -123,7 +122,7 @@ select_socket_from_list(List *socks, int timeout_sec)
                        {
                                ereport(DEBUG2,
                                                (errmsg("wd_hb_recv_socket fd:%d is readable", sock)));
-                               return sock;
+                               return sock;    /* ok */
                        }
                        if (FD_ISSET(sock, &efds))
                        {
@@ -141,9 +140,10 @@ select_socket_from_list(List *socks, int timeout_sec)
        }
        else
        {
+               /* this should never happen */
                ereport(ERROR,
                                (errmsg("failed to get socket data from heartbeat receive socket list"),
-                                errdetail("select() got timeout, exceed %d sec(s)", timeout_sec)));
+                                errdetail("select() returns 0")));
        }
 
        return -1;
@@ -598,11 +598,11 @@ wd_hb_receiver(int fork_wait_time, WdHbIf * hb_if)
                MemoryContextResetAndDeleteChildren(ProcessLoopContext);
 
                /* get readable socket from heartbeat socket list */
-               if ((sock = select_socket_from_list(wd_hb_recv_socks, pool_config->wd_heartbeat_deadtime)) < 0)
+               sock = select_socket_from_list(wd_hb_recv_socks);
+               if (sock < 0)
                {
                        ereport(ERROR, (errmsg("failed to get heartbeat from heartbeat receiver"),
                                                        errdetail("select() failed on heartbeat receiver")));
-                       continue;
                }
 
                /* receive heartbeat signal */