Merge pull request #2991 from jjhursey/fix/ibm/errmgr-help-msg

orte/errmgr: Improve help message on connection lost

Author: Ralph Castain

orte/mca/errmgr/base/help-errmgr-base.txt

@@ -11,6 +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) 2017      IBM Corporation.  All rights reserved.
 # $COPYRIGHT$
 #
 # Additional copyrights may follow
@@ -61,9 +62,10 @@ route found between them. Please check network connectivity
 (including firewalls and network routing requirements).
 #
 [node-died]
-ORTE has lost communication with its daemon located on node:
+ORTE has lost communication with a remote daemon.
 
-  hostname:  %s
+  HNP daemon   : %s on node %s
+  Remote daemon: %s on node %s
 
 This is usually due to either a failure of the TCP network
 connection to the node, or possibly an internal failure of

orte/mca/errmgr/default_hnp/errmgr_default_hnp.c

@@ -10,6 +10,7 @@
  * Copyright (c) 2011-2013 Los Alamos National Security, LLC.
  *                         All rights reserved.
  * Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2017      IBM Corporation.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -379,7 +380,11 @@ static void proc_errors(int fd, short args, void *cbdata)
         /* record the first one to fail */
         if (!ORTE_FLAG_TEST(jdata, ORTE_JOB_FLAG_ABORTED)) {
             /* output an error message so the user knows what happened */
-            orte_show_help("help-errmgr-base.txt", "node-died", true, pptr->node->name);
+            orte_show_help("help-errmgr-base.txt", "node-died", true,
+                           ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
+                           orte_process_info.nodename,
+                           ORTE_NAME_PRINT(proc),
+                           pptr->node->name);
             /* mark the daemon job as failed */
             jdata->state = ORTE_JOB_STATE_COMM_FAILED;
             /* point to the lowest rank to cause the problem */

orte/mca/errmgr/dvm/errmgr_dvm.c

@@ -10,6 +10,7 @@
  * Copyright (c) 2011-2013 Los Alamos National Security, LLC.
  *                         All rights reserved.
  * Copyright (c) 2014-2016 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2017      IBM Corporation.  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -381,7 +382,11 @@ static void proc_errors(int fd, short args, void *cbdata)
         /* record the first one to fail */
         if (!ORTE_FLAG_TEST(jdata, ORTE_JOB_FLAG_ABORTED)) {
             /* output an error message so the user knows what happened */
-            orte_show_help("help-errmgr-base.txt", "node-died", true, pptr->node->name);
+            orte_show_help("help-errmgr-base.txt", "node-died", true,
+                           ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
+                           orte_process_info.nodename,
+                           ORTE_NAME_PRINT(proc),
+                           pptr->node->name);
             /* mark the daemon job as failed */
             jdata->state = ORTE_JOB_STATE_COMM_FAILED;
             /* point to the lowest rank to cause the problem */