Revert part of open-mpi/ompi@c1bbbb5 to restore the usock component, …

…thus fixing show_help aggregation.

Fixes open-mpi#1467

Restore debugger attach operations

Fixes open-mpi#1225

(cherry picked from commit open-mpi/ompi@c146c49)

Fix the debugger attach - previous commit had fixed one instance of a check prior to sending the release message, but there was a second code path that included a similar check that was missed. Thanks to John DelSignore for spotting it!

(cherry picked from commit open-mpi/ompi@4a62377)

Very minor typo

(cherry picked from commit open-mpi/ompi@6e6bbfd)

ompi/mca/rte/orte/rte_orte_module.c

@@ -113,7 +113,7 @@ void ompi_rte_wait_for_debugger(void)
         debugger = 1;
     }
 
-    if (!debugger) {
+    if (!debugger && NULL == getenv("ORTE_TEST_DEBUGGER_ATTACH")) {
         /* if not, just return */
         return;
     }

orte/mca/ess/base/ess_base_std_app.c

@@ -47,9 +47,13 @@
 #include "opal/runtime/opal.h"
 #include "opal/runtime/opal_progress_threads.h"
 
+#include "orte/mca/rml/base/base.h"
+#include "orte/mca/routed/base/base.h"
 #include "orte/mca/errmgr/errmgr.h"
 #include "orte/mca/dfs/base/base.h"
 #include "orte/mca/grpcomm/base/base.h"
+#include "orte/mca/oob/base/base.h"
+#include "orte/mca/rml/rml.h"
 #include "orte/mca/odls/odls_types.h"
 #include "orte/mca/filem/base/base.h"
 #include "orte/mca/errmgr/base/base.h"
@@ -173,14 +177,73 @@ int orte_ess_base_app_setup(bool db_restrict_local)
         }
         OBJ_DESTRUCT(&kv);
     }
-
+    /* Setup the communication infrastructure */
+    /*
+     * OOB Layer
+     */
+    if (ORTE_SUCCESS != (ret = mca_base_framework_open(&orte_oob_base_framework, 0))) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_oob_base_open";
+        goto error;
+    }
+    if (ORTE_SUCCESS != (ret = orte_oob_base_select())) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_oob_base_select";
+        goto error;
+    }
+    /* Runtime Messaging Layer */
+    if (ORTE_SUCCESS != (ret = mca_base_framework_open(&orte_rml_base_framework, 0))) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_rml_base_open";
+        goto error;
+    }
+    if (ORTE_SUCCESS != (ret = orte_rml_base_select())) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_rml_base_select";
+        goto error;
+    }
     /* setup the errmgr */
     if (ORTE_SUCCESS != (ret = orte_errmgr_base_select())) {
         ORTE_ERROR_LOG(ret);
         error = "orte_errmgr_base_select";
         goto error;
     }
-
+    /* Routed system */
+    if (ORTE_SUCCESS != (ret = mca_base_framework_open(&orte_routed_base_framework, 0))) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_routed_base_open";
+        goto error;
+    }
+    if (ORTE_SUCCESS != (ret = orte_routed_base_select())) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_routed_base_select";
+        goto error;
+    }
+    /*
+     * Group communications
+     */
+    if (ORTE_SUCCESS != (ret = mca_base_framework_open(&orte_grpcomm_base_framework, 0))) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_grpcomm_base_open";
+        goto error;
+    }
+    if (ORTE_SUCCESS != (ret = orte_grpcomm_base_select())) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_grpcomm_base_select";
+        goto error;
+    }
+    /* enable communication via the rml */
+    if (ORTE_SUCCESS != (ret = orte_rml.enable_comm())) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_rml.enable_comm";
+        goto error;
+    }
+    /* setup the routed info  */
+    if (ORTE_SUCCESS != (ret = orte_routed.init_routes(ORTE_PROC_MY_NAME->jobid, NULL))) {
+        ORTE_ERROR_LOG(ret);
+        error = "orte_routed.init_routes";
+        goto error;
+    }
     /* open the distributed file system */
     if (ORTE_SUCCESS != (ret = mca_base_framework_open(&orte_dfs_base_framework, 0))) {
         ORTE_ERROR_LOG(ret);
@@ -216,7 +279,13 @@ int orte_ess_base_app_finalize(void)
     (void) mca_base_framework_close(&orte_filem_base_framework);
     (void) mca_base_framework_close(&orte_errmgr_base_framework);
 
+    /* now can close the rml and its friendly group comm */
+    (void) mca_base_framework_close(&orte_grpcomm_base_framework);
     (void) mca_base_framework_close(&orte_dfs_base_framework);
+    (void) mca_base_framework_close(&orte_routed_base_framework);
+
+    (void) mca_base_framework_close(&orte_rml_base_framework);
+    (void) mca_base_framework_close(&orte_oob_base_framework);
     (void) mca_base_framework_close(&orte_state_base_framework);
 
     orte_session_dir_finalize(ORTE_PROC_MY_NAME);
@@ -270,7 +339,7 @@ void orte_ess_base_app_abort(int status, bool report)
      * the message if routing is enabled as this indicates we
      * have someone to send to
      */
-    if (report && orte_create_session_dirs) {
+    if (report && orte_routing_is_enabled && orte_create_session_dirs) {
         myfile = opal_os_path(false, orte_process_info.proc_session_dir, "aborted", NULL);
         fd = open(myfile, O_CREAT, S_IRUSR);
         close(fd);

orte/mca/ess/pmi/ess_pmi_module.c

@@ -47,6 +47,8 @@
 #include "opal/mca/pmix/base/base.h"
 
 #include "orte/mca/errmgr/errmgr.h"
+#include "orte/mca/grpcomm/grpcomm.h"
+#include "orte/mca/rml/rml.h"
 #include "orte/util/proc_info.h"
 #include "orte/util/show_help.h"
 #include "orte/util/name_fns.h"
@@ -83,6 +85,7 @@ static int rte_init(void)
     char *envar, *ev1, *ev2;
     uint64_t unique_key[2];
     char *string_key;
+    char *rmluri;
     opal_value_t *kv;
     char *val;
     int u32, *u32ptr;
@@ -358,6 +361,16 @@ static int rte_init(void)
 
     /***  PUSH DATA FOR OTHERS TO FIND   ***/
 
+    /* push our RML URI in case others need to talk directly to us */
+    rmluri = orte_rml.get_contact_info();
+    /* push it out for others to use */
+    OPAL_MODEX_SEND_VALUE(ret, OPAL_PMIX_GLOBAL, OPAL_PMIX_PROC_URI, rmluri, OPAL_STRING);
+    if (ORTE_SUCCESS != ret) {
+        error = "pmix put uri";
+        goto error;
+    }
+    free(rmluri);
+
     /* push our hostname so others can find us, if they need to */
     OPAL_MODEX_SEND_VALUE(ret, OPAL_PMIX_GLOBAL, OPAL_PMIX_HOSTNAME, orte_process_info.nodename, OPAL_STRING);
     if (ORTE_SUCCESS != ret) {

orte/mca/oob/usock/Makefile.am

@@ -0,0 +1,56 @@
+#
+# Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
+#                         University Research and Technology
+#                         Corporation.  All rights reserved.
+# Copyright (c) 2004-2005 The University of Tennessee and The University
+#                         of Tennessee Research Foundation.  All rights
+#                         reserved.
+# Copyright (c) 2004-2009 High Performance Computing Center Stuttgart,
+#                         University of Stuttgart.  All rights reserved.
+# Copyright (c) 2004-2005 The Regents of the University of California.
+#                         All rights reserved.
+# Copyright (c) 2010      Cisco Systems, Inc.  All rights reserved.
+# Copyright (c) 2012-2013 Los Alamos National Security, LLC.
+#                         All rights reserved
+# Copyright (c) 2013-2015 Intel, Inc. All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+
+sources = \
+          oob_usock_component.h \
+          oob_usock.h \
+          oob_usock_component.c \
+          oob_usock_connection.h \
+          oob_usock_sendrecv.h \
+          oob_usock_hdr.h \
+          oob_usock_peer.h \
+          oob_usock_ping.h \
+          oob_usock.c \
+          oob_usock_connection.c \
+          oob_usock_sendrecv.c
+
+# Make the output library in this directory, and name it either
+# mca_<type>_<name>.la (for DSO builds) or libmca_<type>_<name>.la
+# (for static builds).
+
+if MCA_BUILD_orte_oob_usock_DSO
+component_noinst =
+component_install = mca_oob_usock.la
+else
+component_noinst = libmca_oob_usock.la
+component_install =
+endif
+
+mcacomponentdir = $(ortelibdir)
+mcacomponent_LTLIBRARIES = $(component_install)
+mca_oob_usock_la_SOURCES = $(sources)
+mca_oob_usock_la_LDFLAGS = -module -avoid-version
+
+noinst_LTLIBRARIES = $(component_noinst)
+libmca_oob_usock_la_SOURCES = $(sources)
+libmca_oob_usock_la_LDFLAGS = -module -avoid-version
+

orte/mca/oob/usock/configure.m4

@@ -0,0 +1,42 @@
+# -*- shell-script -*-
+#
+# Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
+#                         University Research and Technology
+#                         Corporation.  All rights reserved.
+# Copyright (c) 2004-2005 The University of Tennessee and The University
+#                         of Tennessee Research Foundation.  All rights
+#                         reserved.
+# Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
+#                         University of Stuttgart.  All rights reserved.
+# Copyright (c) 2004-2005 The Regents of the University of California.
+#                         All rights reserved.
+# Copyright (c) 2011-2013 Los Alamos National Security, LLC.
+#                         All rights reserved.
+# Copyright (c) 2010      Cisco Systems, Inc.  All rights reserved.
+# Copyright (c) 2013      Intel, Inc. All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+
+# MCA_oob_usock_CONFIG([action-if-found], [action-if-not-found])
+# -----------------------------------------------------------
+AC_DEFUN([MCA_orte_oob_usock_CONFIG],[
+    AC_CONFIG_FILES([orte/mca/oob/usock/Makefile])
+
+    # check for sockaddr_un (a good sign we have Unix domain sockets)
+    AC_CHECK_TYPES([struct sockaddr_un],
+                   [oob_usock_happy="yes"],
+                   [oob_usock_happy="no"],
+                   [AC_INCLUDES_DEFAULT
+#ifdef HAVE_SYS_SOCKET_H
+#include <sys/socket.h>
+#endif
+#ifdef HAVE_SYS_UN_H
+#include <sys/un.h>
+#endif])
+
+    AS_IF([test "$oob_usock_happy" = "yes"], [$1], [$2])
+])dnl

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

@@ -0,0 +1,70 @@
+# -*- text -*-
+#
+# Copyright (c) 2004-2006 The Trustees of Indiana University and Indiana
+#                         University Research and Technology
+#                         Corporation.  All rights reserved.
+# Copyright (c) 2004-2006 The University of Tennessee and The University
+#                         of Tennessee Research Foundation.  All rights
+#                         reserved.
+# Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
+#                         University of Stuttgart.  All rights reserved.
+# Copyright (c) 2004-2005 The Regents of the University of California.
+#                         All rights reserved.
+# $COPYRIGHT$
+#
+# Additional copyrights may follow
+#
+# $HEADER$
+#
+[static-and-dynamic]
+Both static and dynamic port ranges were specified for the
+out-of-band (OOB) communication subsystem:
+
+Static ports:   %s
+Dynamic ports:  %s
+
+Only one can be specified. Please choose either static or
+dynamic ports and try again.
+#
+[include-exclude]
+Both TCP interface include and exclude lists were specified:
+
+  Include: %s
+  Exclude: %s
+
+Only one of these can be given.
+#
+[not-parseable]
+The specified network is not parseable. Since we cannot determine
+your desired intent, we cannot establish a TCP socket for out-of-band
+communications and will therefore abort. Please correct the network
+specification and retry.
+#
+[no-included-found]
+None of the networks specified to be included for out-of-band communications
+could be found:
+
+  Value given: %s
+
+Please revise the specification and try again.
+#
+[excluded-all]
+The specified list of networks to be excluded for out-of-band communications
+resulted in no networks being available:
+
+  Value given: %s
+
+Please revise the specification and try again.
+#
+[no-interfaces-avail]
+No network interfaces were found for out-of-band communications. We require
+at least one available network for TCP-based messaging.
+#
+[invalid if_inexclude]
+WARNING: An invalid value was given for oob_tcp_if_%s.  This
+value will be ignored.
+
+  Local host: %s
+  Value:      %s
+  Message:    %s
+#