Merge pull request #5694 from ggouaillardet/topic/v3.0.x/abort_after_finalize

v3.0.x: orte: send error messages to stderr.

Author: hppritcha

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

@@ -12,6 +12,8 @@
 #                         All rights reserved.
 # Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
 # Copyright (c) 2017      IBM Corporation.  All rights reserved.
+# Copyright (c) 2018      Research Organization for Information Science
+#                         and Technology (RIST).  All rights reserved.
 # $COPYRIGHT$
 #
 # Additional copyrights may follow
@@ -105,3 +107,6 @@ An internal error has occurred in ORTE:
 %s
 
 This is something that should be reported to the developers.
+#
+[normal-termination-but]
+%s job %s terminated normally, but %d %s. Per user-direction, the job has been aborted.

orte/mca/errmgr/default_hnp/errmgr_default_hnp.c

@@ -11,6 +11,8 @@
  *                         All rights reserved.
  * Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
  * Copyright (c) 2017      IBM Corporation.  All rights reserved.
+ * Copyright (c) 2018      Research Organization for Information Science
+ *                         and Technology (RIST).  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -840,14 +842,11 @@ static void default_hnp_abort(orte_job_t *jdata)
     i32ptr = &i32;
     if (orte_get_attribute(&jdata->attributes, ORTE_JOB_NUM_NONZERO_EXIT, (void**)&i32ptr, OPAL_INT32)) {
         /* warn user */
-        opal_output(orte_clean_output,
-                    "-------------------------------------------------------\n"
-                    "%s job %s terminated normally, but %d %s. Per user-direction, the job has been aborted.\n"
-                    "-------------------------------------------------------",
-                    (1 == ORTE_LOCAL_JOBID(jdata->jobid)) ? "Primary" : "Child",
-                    (1 == ORTE_LOCAL_JOBID(jdata->jobid)) ? "" : ORTE_LOCAL_JOBID_PRINT(jdata->jobid),
-                    i32, (1 == i32) ? "process returned\na non-zero exit code" :
-                    "processes returned\nnon-zero exit codes");
+        orte_show_help("help-errmgr-base.txt", "normal-termination-but", true, 
+                       (1 == ORTE_LOCAL_JOBID(jdata->jobid)) ? "Primary" : "Child",
+                       (1 == ORTE_LOCAL_JOBID(jdata->jobid)) ? "" : ORTE_LOCAL_JOBID_PRINT(jdata->jobid),
+                       i32, (1 == i32) ? "process returned\na non-zero exit code" :
+                       "processes returned\nnon-zero exit codes");
     }
 
     OPAL_OUTPUT_VERBOSE((1, orte_errmgr_base_framework.framework_output,

orte/mca/state/base/Makefile.am

@@ -1,13 +1,17 @@
 #
 # Copyright (c) 2011-2013 Los Alamos National Security, LLC.
 #                         All rights reserved.
+# Copyright (c) 2018      Research Organization for Information Science
+#                         and Technology (RIST).  All rights reserved.
 # $COPYRIGHT$
 #
 # Additional copyrights may follow
 #
 # $HEADER$
 #
 
+dist_ortedata_DATA += base/help-state-base.txt
+
 headers += \
         base/state_private.h \
         base/base.h

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

@@ -0,0 +1,13 @@
+# -*- text -*-
+#
+# Copyright (c) 2018      Research Organization for Information Science
+#                         and Technology (RIST).  All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+#
+[normal-termination-but]
+While %s job %s terminated normally, %d %s. Further examination may be required.

orte/mca/state/base/state_base_fns.c

@@ -1,6 +1,8 @@
 /*
  * Copyright (c) 2011-2012 Los Alamos National Security, LLC.
  * Copyright (c) 2014-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2018      Research Organization for Information Science
+ *                         and Technology (RIST).  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -38,6 +40,7 @@
 #include "orte/mca/routed/routed.h"
 #include "orte/util/session_dir.h"
 #include "orte/util/threads.h"
+#include "orte/util/show_help.h"
 
 #include "orte/mca/state/base/base.h"
 #include "orte/mca/state/base/state_private.h"
@@ -861,10 +864,7 @@ void orte_state_base_check_all_complete(int fd, short args, void *cbdata)
         }
 
         /* warn user */
-        opal_output(orte_clean_output,
-                    "-------------------------------------------------------\n"
-                    "While %s job %s terminated normally, %d %s. Further examination may be required.\n"
-                    "-------------------------------------------------------",
+        orte_show_help("help-state-base.txt", "normal-termination-but", true,
                     (1 == ORTE_LOCAL_JOBID(jdata->jobid)) ? "the primary" : "child",
                     (1 == ORTE_LOCAL_JOBID(jdata->jobid)) ? "" : ORTE_LOCAL_JOBID_PRINT(jdata->jobid),
                     i32, (1 == i32) ? "process returned\na non-zero exit code." :