oob/tcp: add show_help message about version mismatch

Be more explicit about version mismatch between ORTE processes.

Signed-off-by: Jeff Squyres <[email protected]>

Author: jsquyres

opal/util/fd.c

@@ -24,6 +24,9 @@
 #ifdef HAVE_ARPA_INET_H
 #include <arpa/inet.h>
 #endif
+#ifdef HAVE_NETINET_IN_H
+#include <netinet/in.h>
+#endif
 #ifdef HAVE_UNISTD_H
 #include <unistd.h>
 #endif

orte/mca/oob/tcp/help-oob-tcp.txt

@@ -11,7 +11,7 @@
 # Copyright (c) 2004-2005 The Regents of the University of California.
 #                         All rights reserved.
 # Copyright (c) 2014-2017 Intel, Inc. All rights reserved.
-# Copyright (c) 2015      Cisco Systems, Inc.  All rights reserved.
+# Copyright (c) 2015-2018 Cisco Systems, Inc.  All rights reserved
 # $COPYRIGHT$
 #
 # Additional copyrights may follow
@@ -106,10 +106,29 @@ levels.
   Remote host:     %s
   Remote port:    %d
 
-
 The connection was rejected.
 #
 [static-fwd]
 Static ports were requested while orte_fwd_mpirun_port was set.
 Both options cannot be simultaneously set. Please either set
 orte_fwd_mpirun_port=false or remove any static port directives.
+#
+[version mismatch]
+Open MPI detected a mismatch in versions between two processes.  This
+typically means that you executed "mpirun" (or "mpiexec") from one
+version of Open MPI on on node, but your default path on one of the
+other nodes upon which you launched found a different version of Open
+MPI.
+
+Open MPI only supports running exactly the same version between all
+processes in a single job.
+
+This will almost certainly cause unpredictable behavior, and may end
+up aborting your job.
+
+  Local host:             %s
+  Local process name:     %s
+  Local Open MPI version: %s
+  Peer host:              %s
+  Peer process name:      %s
+  Peer Open MPI version:  %s

orte/mca/oob/tcp/oob_tcp_connection.c

@@ -11,7 +11,7 @@
  *                         All rights reserved.
  * Copyright (c) 2006-2013 Los Alamos National Security, LLC.
  *                         All rights reserved.
- * Copyright (c) 2009-2014 Cisco Systems, Inc.  All rights reserved.
+ * Copyright (c) 2009-2018 Cisco Systems, Inc.  All rights reserved
  * Copyright (c) 2011      Oak Ridge National Labs.  All rights reserved.
  * Copyright (c) 2013-2017 Intel, Inc.  All rights reserved.
  * Copyright (c) 2014-2015 Research Organization for Information Science
@@ -58,6 +58,7 @@
 #include "opal/util/net.h"
 #include "opal/util/fd.h"
 #include "opal/util/error.h"
+#include "opal/util/show_help.h"
 #include "opal/class/opal_hash_table.h"
 #include "opal/mca/event/event.h"
 
@@ -701,6 +702,7 @@ static bool retry(mca_oob_tcp_peer_t* peer, int sd, bool fatal)
     }
 }
 
+
 int mca_oob_tcp_peer_recv_connect_ack(mca_oob_tcp_peer_t* pr,
                                       int sd, mca_oob_tcp_hdr_t *dhdr)
 {
@@ -890,11 +892,15 @@ int mca_oob_tcp_peer_recv_connect_ack(mca_oob_tcp_peer_t* pr,
     version = (char*)((char*)msg + offset);
     offset += strlen(version) + 1;
     if (0 != strcmp(version, orte_version_string)) {
-        opal_output(0, "%s tcp_peer_recv_connect_ack: "
-                    "received different version from %s: %s instead of %s\n",
-                    ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
-                    ORTE_NAME_PRINT(&(peer->name)),
-                    version, orte_version_string);
+        opal_show_help("help-oob-tcp.txt", "version mismatch",
+                       true,
+                       opal_process_info.nodename,
+                       ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
+                       orte_version_string,
+                       opal_fd_get_peer_name(peer->sd),
+                       ORTE_NAME_PRINT(&(peer->name)),
+                       version);
+
         peer->state = MCA_OOB_TCP_FAILED;
         mca_oob_tcp_peer_close(peer);
         free(msg);