1ace83c470
1. minor modification to include two new opal MCA params:
(a) opal_profile: outputs what components were selected by each framework
currently enabled for most, but not all, frameworks
(b) opal_profile_file: name of file that contains profile info required
for modex
2. introduction of two new tools:
(a) ompi-probe: MPI process that simply calls MPI_Init/Finalize with
opal_profile set. Also reports back the rml IP address for all
interfaces on the node
(b) ompi-profiler: uses ompi-probe to create the profile_file, also
reports out a summary of what framework components are actually
being used to help with configuration options
3. modification of the grpcomm basic component to utilize the
profile file in place of the modex where possible
4. modification of orterun so it properly sees opal mca params and
handles opal_profile correctly to ensure we don't get its profile
5. similar mod to orted as for orterun
6. addition of new test that calls orte_init followed by calls to
grpcomm.barrier
This is all completely benign unless actively selected. At the moment, it only supports modex-less launch for openib-based systems. Minor mod to the TCP btl would be required to enable it as well, if people are interested. Similarly, anyone interested in enabling other BTL's for modex-less operation should let me know and I'll give you the magic details.
This seems to significantly improve scalability provided the file can be locally located on the nodes. I'm looking at an alternative means of disseminating the info (perhaps in launch message) as an option for removing that constraint.
This commit was SVN r20098.
109 строки
3.3 KiB
C
109 строки
3.3 KiB
C
/*
|
|
* 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) 2006 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
* Copyright (c) 2008 Cisco Systems, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "opal_config.h"
|
|
|
|
#include <time.h>
|
|
#ifdef HAVE_SIGNAL_H
|
|
#include <signal.h>
|
|
#endif
|
|
|
|
#include "opal/constants.h"
|
|
#include "opal/runtime/opal.h"
|
|
#include "opal/util/output.h"
|
|
#include "opal/util/show_help.h"
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
#include "opal/threads/mutex.h"
|
|
|
|
int opal_register_params(void)
|
|
{
|
|
/*
|
|
* This string is going to be used in opal/util/stacktrace.c
|
|
*/
|
|
{
|
|
char *string = NULL;
|
|
int j;
|
|
int signals[] = {
|
|
#ifdef SIGABRT
|
|
SIGABRT,
|
|
#endif
|
|
#ifdef SIGBUS
|
|
SIGBUS,
|
|
#endif
|
|
#ifdef SIGFPE
|
|
SIGFPE,
|
|
#endif
|
|
#ifdef SIGSEGV
|
|
SIGSEGV,
|
|
#endif
|
|
-1
|
|
};
|
|
for (j = 0 ; signals[j] != -1 ; ++j) {
|
|
if (j == 0) {
|
|
asprintf(&string, "%d", signals[j]);
|
|
} else {
|
|
char *tmp;
|
|
asprintf(&tmp, "%s,%d", string, signals[j]);
|
|
free(string);
|
|
string = tmp;
|
|
}
|
|
}
|
|
|
|
mca_base_param_reg_string_name("opal", "signal",
|
|
"If a signal is received, display the stack trace frame",
|
|
false, false, string, NULL);
|
|
free(string);
|
|
}
|
|
|
|
{
|
|
int j;
|
|
|
|
mca_base_param_reg_int_name("opal", "profile",
|
|
"Set to non-zero to profile component selections",
|
|
false, false, (int)false, &j);
|
|
opal_profile = OPAL_INT_TO_BOOL(j);
|
|
|
|
mca_base_param_reg_string_name("opal", "profile_file",
|
|
"Name of the file containing the cluster configuration information",
|
|
false, false, NULL, &opal_profile_file);
|
|
}
|
|
|
|
#if OMPI_ENABLE_DEBUG
|
|
|
|
|
|
mca_base_param_reg_int_name("opal", "progress_debug",
|
|
"Set to non-zero to debug progress engine features",
|
|
false, false, 0, NULL);
|
|
|
|
{
|
|
int value;
|
|
mca_base_param_reg_int_name("opal", "debug_locks",
|
|
"Debug mutex usage within Open MPI. On a "
|
|
"non-threaded build, this enables integer counters and "
|
|
"warning messages when double-locks are detected.",
|
|
false, false, 0, &value);
|
|
if (value) opal_mutex_check_locks = true;
|
|
}
|
|
#endif
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|