Merge pull request #4814 from rhc54/cmr31/outputfile

Ensure output filename is passed as absolute path

Author: bwbarrett

orte/mca/iof/base/iof_base_frame.c

@@ -13,7 +13,7 @@
  * Copyright (c) 2013      Cisco Systems, Inc.  All rights reserved.
  * Copyright (c) 2015-2017 Intel, Inc.  All rights reserved.
  * Copyright (c) 2015-2018 Research Organization for Information Science
- *                         and Technology (RIST). All rights reserved.
+ *                         and Technology (RIST).  All rights reserved.
  * Copyright (c) 2017      IBM Corporation.  All rights reserved.
  * Copyright (c) 2017      Mellanox Technologies. All rights reserved.
  * $COPYRIGHT$
@@ -111,29 +111,6 @@ static int orte_iof_base_open(mca_base_open_flag_t flags)
 {
     int rc, xmlfd;
 
-    /* did the user request we print output to files? */
-    if (NULL != orte_output_filename) {
-        /* we will setup the files themselves as needed in the iof
-         * module. For now, let's see if the filename contains a
-         * path, or just a name
-         */
-        char *path;
-        path = opal_dirname(orte_output_filename);
-        if (NULL == path) {
-            return ORTE_ERR_OUT_OF_RESOURCE;
-        }
-        if (0 != strcmp(path, orte_output_filename)) {
-            /* there is a path in this name - ensure that the directory
-             * exists, and create it if not
-             */
-            if (ORTE_SUCCESS != (rc = opal_os_dirpath_create(path, S_IRWXU))) {
-                free(path);
-                return rc;
-            }
-        }
-        free(path);
-    }
-
     /* daemons do not need to do this as they do not write out stdout/err */
     if (!ORTE_PROC_IS_DAEMON) {
         if (orte_xml_output) {

orte/mca/plm/base/plm_base_launch_support.c

@@ -14,8 +14,8 @@
  *                         et Automatique. All rights reserved.
  * Copyright (c) 2011-2012 Los Alamos National Security, LLC.
  * Copyright (c) 2013-2018 Intel, Inc.  All rights reserved.
- * Copyright (c) 2014-2017 Research Organization for Information Science
- *                         and Technology (RIST). All rights reserved.
+ * Copyright (c) 2014-2018 Research Organization for Information Science
+ *                         and Technology (RIST).  All rights reserved.
  * Copyright (c) 2016      IBM Corporation.  All rights reserved.
  * $COPYRIGHT$
  *
@@ -1603,13 +1603,6 @@ int orte_plm_base_orted_append_basic_args(int *argc, char ***argv,
         free(param);
     }
 
-    /* if output-filename was specified, pass that along */
-    if (NULL != orte_output_filename) {
-        opal_argv_append(argc, argv, "-"OPAL_MCA_CMD_LINE_ID);
-        opal_argv_append(argc, argv, "orte_output_filename");
-        opal_argv_append(argc, argv, orte_output_filename);
-    }
-
     /* if --xterm was specified, pass that along */
     if (NULL != orte_xterm) {
         opal_argv_append(argc, argv, "-"OPAL_MCA_CMD_LINE_ID);

orte/mca/schizo/ompi/schizo_ompi.c

@@ -14,7 +14,7 @@
  * Copyright (c) 2009-2016 Cisco Systems, Inc.  All rights reserved.
  * Copyright (c) 2011-2017 Oak Ridge National Labs.  All rights reserved.
  * Copyright (c) 2017      UT-Battelle, LLC. All rights reserved.
- * Copyright (c) 2013-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2013-2018 Intel, Inc. All rights reserved.
  * Copyright (c) 2015      Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * $COPYRIGHT$
@@ -139,7 +139,7 @@ static opal_cmd_line_init_t cmd_line_init[] = {
       "Timestamp all application process output", OPAL_CMD_LINE_OTYPE_OUTPUT },
     { "orte_output_filename", '\0', "output-filename", "output-filename", 1,
       &orte_cmd_options.output_filename, OPAL_CMD_LINE_TYPE_STRING,
-      "Redirect output from application processes into filename/job/rank/std[out,err,diag]",
+      "Redirect output from application processes into filename/job/rank/std[out,err,diag]. A relative path value will be converted to an absolute path",
       OPAL_CMD_LINE_OTYPE_OUTPUT },
     { NULL, '\0', "merge-stderr-to-stdout", "merge-stderr-to-stdout", 0,
       &orte_cmd_options.merge, OPAL_CMD_LINE_TYPE_BOOL,

orte/orted/orted_submit.c

@@ -14,7 +14,7 @@
  * Copyright (c) 2007-2009 Sun Microsystems, Inc. All rights reserved.
  * Copyright (c) 2007-2017 Los Alamos National Security, LLC.  All rights
  *                         reserved.
- * Copyright (c) 2013-2017 Intel, Inc.  All rights reserved.
+ * Copyright (c) 2013-2018 Intel, Inc. All rights reserved.
  * Copyright (c) 2015-2017 Research Organization for Information Science
  *                         and Technology (RIST). All rights reserved.
  * Copyright (c) 2017      IBM Corporation.  All rights reserved.
@@ -813,7 +813,19 @@ int orte_submit_job(char *argv[], int *index,
     }
     /* if we were asked to output to files, pass it along */
     if (NULL != orte_cmd_options.output_filename) {
-        orte_set_attribute(&jdata->attributes, ORTE_JOB_OUTPUT_TO_FILE, ORTE_ATTR_GLOBAL, orte_cmd_options.output_filename, OPAL_STRING);
+        /* if the given filename isn't an absolute path, then
+         * convert it to one so the name will be relative to
+         * the directory where prun was given as that is what
+         * the user will have seen */
+        if (!opal_path_is_absolute(orte_cmd_options.output_filename)) {
+            char cwd[OPAL_PATH_MAX], *path;
+            getcwd(cwd, sizeof(cwd));
+            path = opal_os_path(false, cwd, orte_cmd_options.output_filename, NULL);
+            orte_set_attribute(&jdata->attributes, ORTE_JOB_OUTPUT_TO_FILE, ORTE_ATTR_GLOBAL, path, OPAL_STRING);
+            free(path);
+        } else {
+            orte_set_attribute(&jdata->attributes, ORTE_JOB_OUTPUT_TO_FILE, ORTE_ATTR_GLOBAL, orte_cmd_options.output_filename, OPAL_STRING);
+        }
     }
     /* if we were asked to merge stderr to stdout, mark it so */
     if (orte_cmd_options.merge) {

orte/runtime/orte_globals.c

@@ -14,8 +14,8 @@
  * Copyright (c) 2011-2013 Los Alamos National Security, LLC.
  *                         All rights reserved.
  * Copyright (c) 2013-2017 Intel, Inc.  All rights reserved.
- * Copyright (c) 2014-2015 Research Organization for Information Science
- *                         and Technology (RIST). All rights reserved.
+ * Copyright (c) 2014-2018 Research Organization for Information Science
+ *                         and Technology (RIST).  All rights reserved.
  * Copyright (c) 2017      IBM Corporation.  All rights reserved.
  * $COPYRIGHT$
  *
@@ -150,7 +150,6 @@ orte_vpid_t orte_total_procs = 0;
 /* IOF controls */
 bool orte_tag_output = false;
 bool orte_timestamp_output = false;
-char *orte_output_filename = NULL;
 /* generate new xterm windows to display output from specified ranks */
 char *orte_xterm = NULL;
 

orte/runtime/orte_globals.h

@@ -15,6 +15,8 @@
  *                         All rights reserved.
  * Copyright (c) 2013-2017 Intel, Inc.  All rights reserved.
  * Copyright (c) 2017      IBM Corporation.  All rights reserved.
+ * Copyright (c) 2017-2018 Research Organization for Information Science
+ *                         and Technology (RIST).  All rights reserved.
  * $COPYRIGHT$
  *
  * Additional copyrights may follow
@@ -529,7 +531,6 @@ ORTE_DECLSPEC extern orte_vpid_t orte_total_procs;
 /* IOF controls */
 ORTE_DECLSPEC extern bool orte_tag_output;
 ORTE_DECLSPEC extern bool orte_timestamp_output;
-ORTE_DECLSPEC extern char *orte_output_filename;
 /* generate new xterm windows to display output from specified ranks */
 ORTE_DECLSPEC extern char *orte_xterm;
 

orte/runtime/orte_mca_params.c

@@ -14,8 +14,8 @@
  * Copyright (c) 2012-2013 Los Alamos National Security, LLC.
  *                         All rights reserved
  * Copyright (c) 2013-2017 Intel, Inc.  All rights reserved.
- * Copyright (c) 2014      Research Organization for Information Science
- *                         and Technology (RIST). All rights reserved.
+ * Copyright (c) 2014-2018 Research Organization for Information Science
+ *                         and Technology (RIST).  All rights reserved.
  * Copyright (c) 2017      IBM Corporation.  All rights reserved.
  * $COPYRIGHT$
  *
@@ -496,14 +496,6 @@ int orte_register_params(void)
                                   OPAL_INFO_LVL_9, MCA_BASE_VAR_SCOPE_READONLY,
                                   &orte_timestamp_output);
 
-    /* redirect output into files */
-    orte_output_filename = NULL;
-    (void) mca_base_var_register ("orte", "orte", NULL, "output_filename",
-                                  "Redirect output from application processes into filename.rank [default: NULL]",
-                                  MCA_BASE_VAR_TYPE_STRING, NULL, 0, 0,
-                                  OPAL_INFO_LVL_9, MCA_BASE_VAR_SCOPE_READONLY,
-                                  &orte_output_filename);
-
     orte_show_resolved_nodenames = false;
     (void) mca_base_var_register ("orte", "orte", NULL, "show_resolved_nodenames",
                                   "Display any node names that are resolved to a different name (default: false)",

orte/tools/orterun/orterun.1in

@@ -1,7 +1,7 @@
 .\" -*- nroff -*-
 .\" Copyright (c) 2009-2016 Cisco Systems, Inc.  All rights reserved.
 .\" Copyright (c) 2008-2009 Sun Microsystems, Inc.  All rights reserved.
-.\" Copyright (c) 2017      Intel, Inc.  All rights reserved.
+.\" Copyright (c) 2017-2018 Intel, Inc. All rights reserved.
 .\" Copyright (c) 2017      Los Alamos National Security, LLC.  All rights
 .\"                         reserved.
 .\" $COPYRIGHT$
@@ -192,14 +192,14 @@ Number of processes to run.
 .
 .TP
 .B -novm\fR,\fP --novm
-Execute without creating an allocation-spanning virtual machine (only start 
+Execute without creating an allocation-spanning virtual machine (only start
 daemons on nodes hosting application procs).
 .
 .
 .
 .TP
 .B -hnp\fR,\fP --hnp \fR<arg0>\fP
-Specify the URI of the Head Node Process (HNP), or the name of the file (specified as 
+Specify the URI of the Head Node Process (HNP), or the name of the file (specified as
 file:filename) that contains that info.
 .
 .
@@ -330,7 +330,7 @@ each node. (Enabled by default).
 .
 .TP
 .B -oversubscribe\fR,\fP --oversubscribe
-Nodes are allowed to be oversubscribed, even on a managed system, and 
+Nodes are allowed to be oversubscribed, even on a managed system, and
 overloading of processing elements.
 .
 .TP
@@ -414,7 +414,10 @@ Redirect the stdout, stderr, and stddiag of all processes to a process-unique ve
 the specified filename. Any directories in the filename will automatically be created.
 Each output file will consist of filename.id, where the id will be the
 processes' rank in MPI_COMM_WORLD, left-filled with
-zero's for correct ordering in listings.
+zero's for correct ordering in listings. A relative path value will be converted to an
+absolute path based on the cwd where mpirun is executed. Note that this \fIwill not\fP work
+on environments where the file system on compute nodes differs from that where mpirun
+is executed.
 .
 .
 .TP
@@ -724,15 +727,15 @@ Report events to a tool listening at the specified URI.
 .
 .TP
 .B -report-pid\fR,\fP --report-pid \fR<channel>\fP
-Print out mpirun's PID during startup. The channel must be either a '-' to indicate 
-that the pid is to be output to stdout, a '+' to indicate that the pid is to be 
+Print out mpirun's PID during startup. The channel must be either a '-' to indicate
+that the pid is to be output to stdout, a '+' to indicate that the pid is to be
 output to stderr, or a filename to which the pid is to be written.
 .
 .
 .TP
 .B -report-uri\fR,\fP --report-uri \fR<channel>\fP
-Print out mpirun's URI during startup. The channel must be either a '-' to indicate 
-that the URI is to be output to stdout, a '+' to indicate that the URI is to be 
+Print out mpirun's URI during startup. The channel must be either a '-' to indicate
+that the URI is to be output to stdout, a '+' to indicate that the URI is to be
 output to stderr, or a filename to which the URI is to be written.
 .
 .
@@ -1629,7 +1632,7 @@ we return the exit status of the process with the lowest MPI_COMM_WORLD rank to
 .IP \[bu]
 if all processes in the primary job normally terminate with exit status 0, and one or more
 processes in a secondary job normally terminate with non-zero exit status, we (a) return
-the exit status of the process with the lowest MPI_COMM_WORLD rank in the lowest jobid to have a non-zero 
+the exit status of the process with the lowest MPI_COMM_WORLD rank in the lowest jobid to have a non-zero
 status, and (b) output a message summarizing the exit status of the primary and all secondary jobs.
 .IP \[bu]
 if the cmd line option --report-child-jobs-separately is set, we will return -only- the