1
1
openmpi/ompi/tools/ompi_info/ompi_info.c

344 строки
13 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004-2010 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) 2004-2007 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) 2007-2012 Cisco Systems, Inc. All rights reserved.
* Copyright (c) 2011-2012 University of Houston. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#include "ompi_config.h"
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifdef HAVE_NETDB_H
#include <netdb.h>
#endif
#ifdef HAVE_SYS_PARAM_H
#include <sys/param.h>
#endif
#include <errno.h>
#include "opal/mca/installdirs/installdirs.h"
#include "opal/class/opal_object.h"
#include "opal/class/opal_pointer_array.h"
#include "opal/runtime/opal.h"
A number of C/R enhancements per RFC below: http://www.open-mpi.org/community/lists/devel/2010/07/8240.php Documentation: http://osl.iu.edu/research/ft/ Major Changes: -------------- * Added C/R-enabled Debugging support. Enabled with the --enable-crdebug flag. See the following website for more information: http://osl.iu.edu/research/ft/crdebug/ * Added Stable Storage (SStore) framework for checkpoint storage * 'central' component does a direct to central storage save * 'stage' component stages checkpoints to central storage while the application continues execution. * 'stage' supports offline compression of checkpoints before moving (sstore_stage_compress) * 'stage' supports local caching of checkpoints to improve automatic recovery (sstore_stage_caching) * Added Compression (compress) framework to support * Add two new ErrMgr recovery policies * {{{crmig}}} C/R Process Migration * {{{autor}}} C/R Automatic Recovery * Added the {{{ompi-migrate}}} command line tool to support the {{{crmig}}} ErrMgr component * Added CR MPI Ext functions (enable them with {{{--enable-mpi-ext=cr}}} configure option) * {{{OMPI_CR_Checkpoint}}} (Fixes trac:2342) * {{{OMPI_CR_Restart}}} * {{{OMPI_CR_Migrate}}} (may need some more work for mapping rules) * {{{OMPI_CR_INC_register_callback}}} (Fixes trac:2192) * {{{OMPI_CR_Quiesce_start}}} * {{{OMPI_CR_Quiesce_checkpoint}}} * {{{OMPI_CR_Quiesce_end}}} * {{{OMPI_CR_self_register_checkpoint_callback}}} * {{{OMPI_CR_self_register_restart_callback}}} * {{{OMPI_CR_self_register_continue_callback}}} * The ErrMgr predicted_fault() interface has been changed to take an opal_list_t of ErrMgr defined types. This will allow us to better support a wider range of fault prediction services in the future. * Add a progress meter to: * FileM rsh (filem_rsh_process_meter) * SnapC full (snapc_full_progress_meter) * SStore stage (sstore_stage_progress_meter) * Added 2 new command line options to ompi-restart * --showme : Display the full command line that would have been exec'ed. * --mpirun_opts : Command line options to pass directly to mpirun. (Fixes trac:2413) * Deprecated some MCA params: * crs_base_snapshot_dir deprecated, use sstore_stage_local_snapshot_dir * snapc_base_global_snapshot_dir deprecated, use sstore_base_global_snapshot_dir * snapc_base_global_shared deprecated, use sstore_stage_global_is_shared * snapc_base_store_in_place deprecated, replaced with different components of SStore * snapc_base_global_snapshot_ref deprecated, use sstore_base_global_snapshot_ref * snapc_base_establish_global_snapshot_dir deprecated, never well supported * snapc_full_skip_filem deprecated, use sstore_stage_skip_filem Minor Changes: -------------- * Fixes trac:1924 : {{{ompi-restart}}} now recognizes path prefixed checkpoint handles and does the right thing. * Fixes trac:2097 : {{{ompi-info}}} should now report all available CRS components * Fixes trac:2161 : Manual checkpoint movement. A user can 'mv' a checkpoint directory from the original location to another and still restart from it. * Fixes trac:2208 : Honor various TMPDIR varaibles instead of forcing {{{/tmp}}} * Move {{{ompi_cr_continue_like_restart}}} to {{{orte_cr_continue_like_restart}}} to be more flexible in where this should be set. * opal_crs_base_metadata_write* functions have been moved to SStore to support a wider range of metadata handling functionality. * Cleanup the CRS framework and components to work with the SStore framework. * Cleanup the SnapC framework and components to work with the SStore framework (cleans up these code paths considerably). * Add 'quiesce' hook to CRCP for a future enhancement. * We now require a BLCR version that supports {{{cr_request_file()}}} or {{{cr_request_checkpoint()}}} in order to make the code more maintainable. Note that {{{cr_request_file}}} has been deprecated since 0.7.0, so we prefer to use {{{cr_request_checkpoint()}}}. * Add optional application level INC callbacks (registered through the CR MPI Ext interface). * Increase the {{{opal_cr_thread_sleep_wait}}} parameter to 1000 microseconds to make the C/R thread less aggressive. * {{{opal-restart}}} now looks for cache directories before falling back on stable storage when asked. * {{{opal-restart}}} also support local decompression before restarting * {{{orte-checkpoint}}} now uses the SStore framework to work with the metadata * {{{orte-restart}}} now uses the SStore framework to work with the metadata * Remove the {{{orte-restart}}} preload option. This was removed since the user only needs to select the 'stage' component in order to support this functionality. * Since the '-am' parameter is saved in the metadata, {{{ompi-restart}}} no longer hard codes {{{-am ft-enable-cr}}}. * Fix {{{hnp}}} ErrMgr so that if a previous component in the stack has 'fixed' the problem, then it should be skipped. * Make sure to decrement the number of 'num_local_procs' in the orted when one goes away. * odls now checks the SStore framework to see if it needs to load any checkpoint files before launching (to support 'stage'). This separates the SStore logic from the --preload-[binary|files] options. * Add unique IDs to the named pipes established between the orted and the app in SnapC. This is to better support migration and automatic recovery activities. * Improve the checks for 'already checkpointing' error path. * A a recovery output timer, to show how long it takes to restart a job * Do a better job of cleaning up the old session directory on restart. * Add a local module to the autor and crmig ErrMgr components. These small modules prevent the 'orted' component from attempting a local recovery (Which does not work for MPI apps at the moment) * Add a fix for bounding the checkpointable region between MPI_Init and MPI_Finalize. This commit was SVN r23587. The following Trac tickets were found above: Ticket 1924 --> https://svn.open-mpi.org/trac/ompi/ticket/1924 Ticket 2097 --> https://svn.open-mpi.org/trac/ompi/ticket/2097 Ticket 2161 --> https://svn.open-mpi.org/trac/ompi/ticket/2161 Ticket 2192 --> https://svn.open-mpi.org/trac/ompi/ticket/2192 Ticket 2208 --> https://svn.open-mpi.org/trac/ompi/ticket/2208 Ticket 2342 --> https://svn.open-mpi.org/trac/ompi/ticket/2342 Ticket 2413 --> https://svn.open-mpi.org/trac/ompi/ticket/2413
2010-08-11 00:51:11 +04:00
#if OPAL_ENABLE_FT_CR == 1
#include "opal/runtime/opal_cr.h"
#endif
#include "opal/util/cmd_line.h"
#include "opal/util/error.h"
#include "opal/util/argv.h"
#include "opal/util/show_help.h"
#include "opal/mca/base/base.h"
#include "orte/util/show_help.h"
#include "ompi/communicator/communicator.h"
#include "ompi/tools/ompi_info/ompi_info.h"
/*
* Public variables
*/
bool ompi_info_pretty = true;
opal_cmd_line_t *ompi_info_cmd_line = NULL;
const char *ompi_info_type_all = "all";
const char *ompi_info_type_ompi = "ompi";
const char *ompi_info_type_orte = "orte";
const char *ompi_info_type_opal = "opal";
const char *ompi_info_type_base = "base";
opal_pointer_array_t mca_types;
int main(int argc, char *argv[])
{
int ret = 0;
bool want_help = false;
bool cmd_error = false;
bool acted = false;
bool want_all = false;
char **app_env = NULL, **global_env = NULL;
int i, len;
char *str;
/* Initialize the argv parsing handle */
if (OMPI_SUCCESS != opal_init_util(&argc, &argv)) {
orte_show_help("help-ompi_info.txt", "lib-call-fail", true,
"opal_init_util", __FILE__, __LINE__, NULL);
exit(ret);
}
ompi_info_cmd_line = OBJ_NEW(opal_cmd_line_t);
if (NULL == ompi_info_cmd_line) {
ret = errno;
orte_show_help("help-ompi_info.txt", "lib-call-fail", true,
"opal_cmd_line_create", __FILE__, __LINE__, NULL);
opal_finalize_util();
exit(ret);
}
opal_cmd_line_make_opt3(ompi_info_cmd_line, 'v', NULL, "version", 2,
"Show version of Open MPI or a component. The first parameter can be the keywords \"ompi\" or \"all\", a framework name (indicating all components in a framework), or a framework:component string (indicating a specific component). The second parameter can be one of: full, major, minor, release, greek, svn.");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "param", 2,
"Show MCA parameters. The first parameter is the framework (or the keyword \"all\"); the second parameter is the specific component name (or the keyword \"all\").");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "internal", 0,
"Show internal MCA parameters (not meant to be modified by users)");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "path", 1,
"Show paths that Open MPI was configured with. Accepts the following parameters: prefix, bindir, libdir, incdir, mandir, pkglibdir, sysconfdir");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "arch", 0,
"Show architecture Open MPI was compiled on");
opal_cmd_line_make_opt3(ompi_info_cmd_line, 'c', NULL, "config", 0,
"Show configuration options");
opal_cmd_line_make_opt3(ompi_info_cmd_line, 'h', NULL, "help", 0,
"Show this help message");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "ompi_info_pretty", 0,
"When used in conjunction with other parameters, the output is displayed in 'ompi_info_prettyprint' format (default)");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "parsable", 0,
"When used in conjunction with other parameters, the output is displayed in a machine-parsable format");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "parseable", 0,
"Synonym for --parsable");
opal_cmd_line_make_opt3(ompi_info_cmd_line, '\0', NULL, "hostname", 0,
"Show the hostname that Open MPI was configured "
"and built on");
opal_cmd_line_make_opt3(ompi_info_cmd_line, 'a', NULL, "all", 0,
"Show all configuration options and MCA parameters");
/* Call some useless functions in order to guarantee to link in some
* global variables. Only check the return value so that the
* compiler doesn't optimize out the useless function.
*/
if (OMPI_SUCCESS != ompi_comm_link_function()) {
/* Stop .. or I'll say stop again! */
++ret;
} else {
--ret;
}
/* set our threading level */
opal_set_using_threads(false);
/* Get MCA parameters, if any */
if( OMPI_SUCCESS != mca_base_open() ) {
orte_show_help("help-ompi_info.txt", "lib-call-fail", true, "mca_base_open", __FILE__, __LINE__ );
OBJ_RELEASE(ompi_info_cmd_line);
opal_finalize_util();
exit(1);
}
mca_base_cmd_line_setup(ompi_info_cmd_line);
/* Do the parsing */
ret = opal_cmd_line_parse(ompi_info_cmd_line, false, argc, argv);
if (OMPI_SUCCESS != ret) {
cmd_error = true;
if (OPAL_ERR_SILENT != ret) {
fprintf(stderr, "%s: command line error (%s)\n", argv[0],
opal_strerror(ret));
}
}
if (!cmd_error &&
(opal_cmd_line_is_taken(ompi_info_cmd_line, "help") ||
opal_cmd_line_is_taken(ompi_info_cmd_line, "h"))) {
char *str, *usage;
want_help = true;
usage = opal_cmd_line_get_usage_msg(ompi_info_cmd_line);
str = opal_show_help_string("help-ompi_info.txt", "usage",
true, usage);
if (NULL != str) {
printf("%s", str);
free(str);
}
free(usage);
}
/* If we had a cmd line parse error, or we showed the help
message, it's time to exit. */
if (cmd_error || want_help) {
mca_base_close();
OBJ_RELEASE(ompi_info_cmd_line);
opal_finalize_util();
exit(cmd_error ? 1 : 0);
}
mca_base_cmd_line_process_args(ompi_info_cmd_line, &app_env, &global_env);
/* putenv() all the stuff that we got back from env (in case the
* user specified some --mca params on the command line). This
* creates a memory leak, but that's unfortunately how putenv()
* works. :-(
*/
len = opal_argv_count(app_env);
for (i = 0; i < len; ++i) {
putenv(app_env[i]);
}
len = opal_argv_count(global_env);
for (i = 0; i < len; ++i) {
putenv(global_env[i]);
}
/* setup the mca_types array */
OBJ_CONSTRUCT(&mca_types, opal_pointer_array_t);
opal_pointer_array_init(&mca_types, 256, INT_MAX, 128);
opal_pointer_array_add(&mca_types, "mca");
opal_pointer_array_add(&mca_types, "mpi");
opal_pointer_array_add(&mca_types, "orte");
opal_pointer_array_add(&mca_types, "opal");
opal_pointer_array_add(&mca_types, "filter");
opal_pointer_array_add(&mca_types, "backtrace");
opal_pointer_array_add(&mca_types, "memchecker");
opal_pointer_array_add(&mca_types, "memory");
opal_pointer_array_add(&mca_types, "shmem");
opal_pointer_array_add(&mca_types, "timer");
opal_pointer_array_add(&mca_types, "installdirs");
opal_pointer_array_add(&mca_types, "hwloc");
#if OPAL_ENABLE_FT_CR == 1
A number of C/R enhancements per RFC below: http://www.open-mpi.org/community/lists/devel/2010/07/8240.php Documentation: http://osl.iu.edu/research/ft/ Major Changes: -------------- * Added C/R-enabled Debugging support. Enabled with the --enable-crdebug flag. See the following website for more information: http://osl.iu.edu/research/ft/crdebug/ * Added Stable Storage (SStore) framework for checkpoint storage * 'central' component does a direct to central storage save * 'stage' component stages checkpoints to central storage while the application continues execution. * 'stage' supports offline compression of checkpoints before moving (sstore_stage_compress) * 'stage' supports local caching of checkpoints to improve automatic recovery (sstore_stage_caching) * Added Compression (compress) framework to support * Add two new ErrMgr recovery policies * {{{crmig}}} C/R Process Migration * {{{autor}}} C/R Automatic Recovery * Added the {{{ompi-migrate}}} command line tool to support the {{{crmig}}} ErrMgr component * Added CR MPI Ext functions (enable them with {{{--enable-mpi-ext=cr}}} configure option) * {{{OMPI_CR_Checkpoint}}} (Fixes trac:2342) * {{{OMPI_CR_Restart}}} * {{{OMPI_CR_Migrate}}} (may need some more work for mapping rules) * {{{OMPI_CR_INC_register_callback}}} (Fixes trac:2192) * {{{OMPI_CR_Quiesce_start}}} * {{{OMPI_CR_Quiesce_checkpoint}}} * {{{OMPI_CR_Quiesce_end}}} * {{{OMPI_CR_self_register_checkpoint_callback}}} * {{{OMPI_CR_self_register_restart_callback}}} * {{{OMPI_CR_self_register_continue_callback}}} * The ErrMgr predicted_fault() interface has been changed to take an opal_list_t of ErrMgr defined types. This will allow us to better support a wider range of fault prediction services in the future. * Add a progress meter to: * FileM rsh (filem_rsh_process_meter) * SnapC full (snapc_full_progress_meter) * SStore stage (sstore_stage_progress_meter) * Added 2 new command line options to ompi-restart * --showme : Display the full command line that would have been exec'ed. * --mpirun_opts : Command line options to pass directly to mpirun. (Fixes trac:2413) * Deprecated some MCA params: * crs_base_snapshot_dir deprecated, use sstore_stage_local_snapshot_dir * snapc_base_global_snapshot_dir deprecated, use sstore_base_global_snapshot_dir * snapc_base_global_shared deprecated, use sstore_stage_global_is_shared * snapc_base_store_in_place deprecated, replaced with different components of SStore * snapc_base_global_snapshot_ref deprecated, use sstore_base_global_snapshot_ref * snapc_base_establish_global_snapshot_dir deprecated, never well supported * snapc_full_skip_filem deprecated, use sstore_stage_skip_filem Minor Changes: -------------- * Fixes trac:1924 : {{{ompi-restart}}} now recognizes path prefixed checkpoint handles and does the right thing. * Fixes trac:2097 : {{{ompi-info}}} should now report all available CRS components * Fixes trac:2161 : Manual checkpoint movement. A user can 'mv' a checkpoint directory from the original location to another and still restart from it. * Fixes trac:2208 : Honor various TMPDIR varaibles instead of forcing {{{/tmp}}} * Move {{{ompi_cr_continue_like_restart}}} to {{{orte_cr_continue_like_restart}}} to be more flexible in where this should be set. * opal_crs_base_metadata_write* functions have been moved to SStore to support a wider range of metadata handling functionality. * Cleanup the CRS framework and components to work with the SStore framework. * Cleanup the SnapC framework and components to work with the SStore framework (cleans up these code paths considerably). * Add 'quiesce' hook to CRCP for a future enhancement. * We now require a BLCR version that supports {{{cr_request_file()}}} or {{{cr_request_checkpoint()}}} in order to make the code more maintainable. Note that {{{cr_request_file}}} has been deprecated since 0.7.0, so we prefer to use {{{cr_request_checkpoint()}}}. * Add optional application level INC callbacks (registered through the CR MPI Ext interface). * Increase the {{{opal_cr_thread_sleep_wait}}} parameter to 1000 microseconds to make the C/R thread less aggressive. * {{{opal-restart}}} now looks for cache directories before falling back on stable storage when asked. * {{{opal-restart}}} also support local decompression before restarting * {{{orte-checkpoint}}} now uses the SStore framework to work with the metadata * {{{orte-restart}}} now uses the SStore framework to work with the metadata * Remove the {{{orte-restart}}} preload option. This was removed since the user only needs to select the 'stage' component in order to support this functionality. * Since the '-am' parameter is saved in the metadata, {{{ompi-restart}}} no longer hard codes {{{-am ft-enable-cr}}}. * Fix {{{hnp}}} ErrMgr so that if a previous component in the stack has 'fixed' the problem, then it should be skipped. * Make sure to decrement the number of 'num_local_procs' in the orted when one goes away. * odls now checks the SStore framework to see if it needs to load any checkpoint files before launching (to support 'stage'). This separates the SStore logic from the --preload-[binary|files] options. * Add unique IDs to the named pipes established between the orted and the app in SnapC. This is to better support migration and automatic recovery activities. * Improve the checks for 'already checkpointing' error path. * A a recovery output timer, to show how long it takes to restart a job * Do a better job of cleaning up the old session directory on restart. * Add a local module to the autor and crmig ErrMgr components. These small modules prevent the 'orted' component from attempting a local recovery (Which does not work for MPI apps at the moment) * Add a fix for bounding the checkpointable region between MPI_Init and MPI_Finalize. This commit was SVN r23587. The following Trac tickets were found above: Ticket 1924 --> https://svn.open-mpi.org/trac/ompi/ticket/1924 Ticket 2097 --> https://svn.open-mpi.org/trac/ompi/ticket/2097 Ticket 2161 --> https://svn.open-mpi.org/trac/ompi/ticket/2161 Ticket 2192 --> https://svn.open-mpi.org/trac/ompi/ticket/2192 Ticket 2208 --> https://svn.open-mpi.org/trac/ompi/ticket/2208 Ticket 2342 --> https://svn.open-mpi.org/trac/ompi/ticket/2342 Ticket 2413 --> https://svn.open-mpi.org/trac/ompi/ticket/2413
2010-08-11 00:51:11 +04:00
opal_cr_set_enabled(true);
opal_pointer_array_add(&mca_types, "crs");
A number of C/R enhancements per RFC below: http://www.open-mpi.org/community/lists/devel/2010/07/8240.php Documentation: http://osl.iu.edu/research/ft/ Major Changes: -------------- * Added C/R-enabled Debugging support. Enabled with the --enable-crdebug flag. See the following website for more information: http://osl.iu.edu/research/ft/crdebug/ * Added Stable Storage (SStore) framework for checkpoint storage * 'central' component does a direct to central storage save * 'stage' component stages checkpoints to central storage while the application continues execution. * 'stage' supports offline compression of checkpoints before moving (sstore_stage_compress) * 'stage' supports local caching of checkpoints to improve automatic recovery (sstore_stage_caching) * Added Compression (compress) framework to support * Add two new ErrMgr recovery policies * {{{crmig}}} C/R Process Migration * {{{autor}}} C/R Automatic Recovery * Added the {{{ompi-migrate}}} command line tool to support the {{{crmig}}} ErrMgr component * Added CR MPI Ext functions (enable them with {{{--enable-mpi-ext=cr}}} configure option) * {{{OMPI_CR_Checkpoint}}} (Fixes trac:2342) * {{{OMPI_CR_Restart}}} * {{{OMPI_CR_Migrate}}} (may need some more work for mapping rules) * {{{OMPI_CR_INC_register_callback}}} (Fixes trac:2192) * {{{OMPI_CR_Quiesce_start}}} * {{{OMPI_CR_Quiesce_checkpoint}}} * {{{OMPI_CR_Quiesce_end}}} * {{{OMPI_CR_self_register_checkpoint_callback}}} * {{{OMPI_CR_self_register_restart_callback}}} * {{{OMPI_CR_self_register_continue_callback}}} * The ErrMgr predicted_fault() interface has been changed to take an opal_list_t of ErrMgr defined types. This will allow us to better support a wider range of fault prediction services in the future. * Add a progress meter to: * FileM rsh (filem_rsh_process_meter) * SnapC full (snapc_full_progress_meter) * SStore stage (sstore_stage_progress_meter) * Added 2 new command line options to ompi-restart * --showme : Display the full command line that would have been exec'ed. * --mpirun_opts : Command line options to pass directly to mpirun. (Fixes trac:2413) * Deprecated some MCA params: * crs_base_snapshot_dir deprecated, use sstore_stage_local_snapshot_dir * snapc_base_global_snapshot_dir deprecated, use sstore_base_global_snapshot_dir * snapc_base_global_shared deprecated, use sstore_stage_global_is_shared * snapc_base_store_in_place deprecated, replaced with different components of SStore * snapc_base_global_snapshot_ref deprecated, use sstore_base_global_snapshot_ref * snapc_base_establish_global_snapshot_dir deprecated, never well supported * snapc_full_skip_filem deprecated, use sstore_stage_skip_filem Minor Changes: -------------- * Fixes trac:1924 : {{{ompi-restart}}} now recognizes path prefixed checkpoint handles and does the right thing. * Fixes trac:2097 : {{{ompi-info}}} should now report all available CRS components * Fixes trac:2161 : Manual checkpoint movement. A user can 'mv' a checkpoint directory from the original location to another and still restart from it. * Fixes trac:2208 : Honor various TMPDIR varaibles instead of forcing {{{/tmp}}} * Move {{{ompi_cr_continue_like_restart}}} to {{{orte_cr_continue_like_restart}}} to be more flexible in where this should be set. * opal_crs_base_metadata_write* functions have been moved to SStore to support a wider range of metadata handling functionality. * Cleanup the CRS framework and components to work with the SStore framework. * Cleanup the SnapC framework and components to work with the SStore framework (cleans up these code paths considerably). * Add 'quiesce' hook to CRCP for a future enhancement. * We now require a BLCR version that supports {{{cr_request_file()}}} or {{{cr_request_checkpoint()}}} in order to make the code more maintainable. Note that {{{cr_request_file}}} has been deprecated since 0.7.0, so we prefer to use {{{cr_request_checkpoint()}}}. * Add optional application level INC callbacks (registered through the CR MPI Ext interface). * Increase the {{{opal_cr_thread_sleep_wait}}} parameter to 1000 microseconds to make the C/R thread less aggressive. * {{{opal-restart}}} now looks for cache directories before falling back on stable storage when asked. * {{{opal-restart}}} also support local decompression before restarting * {{{orte-checkpoint}}} now uses the SStore framework to work with the metadata * {{{orte-restart}}} now uses the SStore framework to work with the metadata * Remove the {{{orte-restart}}} preload option. This was removed since the user only needs to select the 'stage' component in order to support this functionality. * Since the '-am' parameter is saved in the metadata, {{{ompi-restart}}} no longer hard codes {{{-am ft-enable-cr}}}. * Fix {{{hnp}}} ErrMgr so that if a previous component in the stack has 'fixed' the problem, then it should be skipped. * Make sure to decrement the number of 'num_local_procs' in the orted when one goes away. * odls now checks the SStore framework to see if it needs to load any checkpoint files before launching (to support 'stage'). This separates the SStore logic from the --preload-[binary|files] options. * Add unique IDs to the named pipes established between the orted and the app in SnapC. This is to better support migration and automatic recovery activities. * Improve the checks for 'already checkpointing' error path. * A a recovery output timer, to show how long it takes to restart a job * Do a better job of cleaning up the old session directory on restart. * Add a local module to the autor and crmig ErrMgr components. These small modules prevent the 'orted' component from attempting a local recovery (Which does not work for MPI apps at the moment) * Add a fix for bounding the checkpointable region between MPI_Init and MPI_Finalize. This commit was SVN r23587. The following Trac tickets were found above: Ticket 1924 --> https://svn.open-mpi.org/trac/ompi/ticket/1924 Ticket 2097 --> https://svn.open-mpi.org/trac/ompi/ticket/2097 Ticket 2161 --> https://svn.open-mpi.org/trac/ompi/ticket/2161 Ticket 2192 --> https://svn.open-mpi.org/trac/ompi/ticket/2192 Ticket 2208 --> https://svn.open-mpi.org/trac/ompi/ticket/2208 Ticket 2342 --> https://svn.open-mpi.org/trac/ompi/ticket/2342 Ticket 2413 --> https://svn.open-mpi.org/trac/ompi/ticket/2413
2010-08-11 00:51:11 +04:00
opal_pointer_array_add(&mca_types, "compress");
#endif
opal_pointer_array_add(&mca_types, "if");
Update libevent to the 2.0 series, currently at 2.0.7rc. We will update to their final release when it becomes available. Currently known errors exist in unused portions of the libevent code. This revision passes the IBM test suite on a Linux machine and on a standalone Mac. This is a fairly intrusive change, but outside of the moving of opal/event to opal/mca/event, the only changes involved (a) changing all calls to opal_event functions to reflect the new framework instead, and (b) ensuring that all opal_event_t objects are properly constructed since they are now true opal_objects. Note: Shiqing has just returned from vacation and has not yet had a chance to complete the Windows integration. Thus, this commit almost certainly breaks Windows support on the trunk. However, I want this to have a chance to soak for as long as possible before I become less available a week from today (going to be at a class for 5 days, and thus will only be sparingly available) so we can find and fix any problems. Biggest change is moving the libevent code from opal/event to a new opal/mca/event framework. This was done to make it much easier to update libevent in the future. New versions can be inserted as a new component and tested in parallel with the current version until validated, then we can remove the earlier version if we so choose. This is a statically built framework ala installdirs, so only one component will build at a time. There is no selection logic - the sole compiled component simply loads its function pointers into the opal_event struct. I have gone thru the code base and converted all the libevent calls I could find. However, I cannot compile nor test every environment. It is therefore quite likely that errors remain in the system. Please keep an eye open for two things: 1. compile-time errors: these will be obvious as calls to the old functions (e.g., opal_evtimer_new) must be replaced by the new framework APIs (e.g., opal_event.evtimer_new) 2. run-time errors: these will likely show up as segfaults due to missing constructors on opal_event_t objects. It appears that it became a typical practice for people to "init" an opal_event_t by simply using memset to zero it out. This will no longer work - you must either OBJ_NEW or OBJ_CONSTRUCT an opal_event_t. I tried to catch these cases, but may have missed some. Believe me, you'll know when you hit it. There is also the issue of the new libevent "no recursion" behavior. As I described on a recent email, we will have to discuss this and figure out what, if anything, we need to do. This commit was SVN r23925.
2010-10-24 22:35:54 +04:00
opal_pointer_array_add(&mca_types, "event");
opal_pointer_array_add(&mca_types, "dpm");
opal_pointer_array_add(&mca_types, "pubsub");
opal_pointer_array_add(&mca_types, "allocator");
opal_pointer_array_add(&mca_types, "coll");
opal_pointer_array_add(&mca_types, "io");
opal_pointer_array_add(&mca_types, "mpool");
opal_pointer_array_add(&mca_types, "pml");
opal_pointer_array_add(&mca_types, "bml");
opal_pointer_array_add(&mca_types, "rcache");
opal_pointer_array_add(&mca_types, "btl");
opal_pointer_array_add(&mca_types, "mtl");
opal_pointer_array_add(&mca_types, "topo");
opal_pointer_array_add(&mca_types, "osc");
opal_pointer_array_add(&mca_types, "op");
opal_pointer_array_add(&mca_types, "common");
opal_pointer_array_add(&mca_types, "fbtl");
opal_pointer_array_add(&mca_types, "fs");
opal_pointer_array_add(&mca_types, "fcoll");
opal_pointer_array_add(&mca_types, "sharedfp");
#if OPAL_ENABLE_FT_CR == 1
opal_pointer_array_add(&mca_types, "crcp");
#endif
#if !ORTE_DISABLE_FULL_SUPPORT
opal_pointer_array_add(&mca_types, "iof");
opal_pointer_array_add(&mca_types, "oob");
opal_pointer_array_add(&mca_types, "odls");
opal_pointer_array_add(&mca_types, "ras");
opal_pointer_array_add(&mca_types, "rmaps");
opal_pointer_array_add(&mca_types, "rml");
opal_pointer_array_add(&mca_types, "routed");
opal_pointer_array_add(&mca_types, "plm");
#if OPAL_ENABLE_FT_CR == 1
A number of C/R enhancements per RFC below: http://www.open-mpi.org/community/lists/devel/2010/07/8240.php Documentation: http://osl.iu.edu/research/ft/ Major Changes: -------------- * Added C/R-enabled Debugging support. Enabled with the --enable-crdebug flag. See the following website for more information: http://osl.iu.edu/research/ft/crdebug/ * Added Stable Storage (SStore) framework for checkpoint storage * 'central' component does a direct to central storage save * 'stage' component stages checkpoints to central storage while the application continues execution. * 'stage' supports offline compression of checkpoints before moving (sstore_stage_compress) * 'stage' supports local caching of checkpoints to improve automatic recovery (sstore_stage_caching) * Added Compression (compress) framework to support * Add two new ErrMgr recovery policies * {{{crmig}}} C/R Process Migration * {{{autor}}} C/R Automatic Recovery * Added the {{{ompi-migrate}}} command line tool to support the {{{crmig}}} ErrMgr component * Added CR MPI Ext functions (enable them with {{{--enable-mpi-ext=cr}}} configure option) * {{{OMPI_CR_Checkpoint}}} (Fixes trac:2342) * {{{OMPI_CR_Restart}}} * {{{OMPI_CR_Migrate}}} (may need some more work for mapping rules) * {{{OMPI_CR_INC_register_callback}}} (Fixes trac:2192) * {{{OMPI_CR_Quiesce_start}}} * {{{OMPI_CR_Quiesce_checkpoint}}} * {{{OMPI_CR_Quiesce_end}}} * {{{OMPI_CR_self_register_checkpoint_callback}}} * {{{OMPI_CR_self_register_restart_callback}}} * {{{OMPI_CR_self_register_continue_callback}}} * The ErrMgr predicted_fault() interface has been changed to take an opal_list_t of ErrMgr defined types. This will allow us to better support a wider range of fault prediction services in the future. * Add a progress meter to: * FileM rsh (filem_rsh_process_meter) * SnapC full (snapc_full_progress_meter) * SStore stage (sstore_stage_progress_meter) * Added 2 new command line options to ompi-restart * --showme : Display the full command line that would have been exec'ed. * --mpirun_opts : Command line options to pass directly to mpirun. (Fixes trac:2413) * Deprecated some MCA params: * crs_base_snapshot_dir deprecated, use sstore_stage_local_snapshot_dir * snapc_base_global_snapshot_dir deprecated, use sstore_base_global_snapshot_dir * snapc_base_global_shared deprecated, use sstore_stage_global_is_shared * snapc_base_store_in_place deprecated, replaced with different components of SStore * snapc_base_global_snapshot_ref deprecated, use sstore_base_global_snapshot_ref * snapc_base_establish_global_snapshot_dir deprecated, never well supported * snapc_full_skip_filem deprecated, use sstore_stage_skip_filem Minor Changes: -------------- * Fixes trac:1924 : {{{ompi-restart}}} now recognizes path prefixed checkpoint handles and does the right thing. * Fixes trac:2097 : {{{ompi-info}}} should now report all available CRS components * Fixes trac:2161 : Manual checkpoint movement. A user can 'mv' a checkpoint directory from the original location to another and still restart from it. * Fixes trac:2208 : Honor various TMPDIR varaibles instead of forcing {{{/tmp}}} * Move {{{ompi_cr_continue_like_restart}}} to {{{orte_cr_continue_like_restart}}} to be more flexible in where this should be set. * opal_crs_base_metadata_write* functions have been moved to SStore to support a wider range of metadata handling functionality. * Cleanup the CRS framework and components to work with the SStore framework. * Cleanup the SnapC framework and components to work with the SStore framework (cleans up these code paths considerably). * Add 'quiesce' hook to CRCP for a future enhancement. * We now require a BLCR version that supports {{{cr_request_file()}}} or {{{cr_request_checkpoint()}}} in order to make the code more maintainable. Note that {{{cr_request_file}}} has been deprecated since 0.7.0, so we prefer to use {{{cr_request_checkpoint()}}}. * Add optional application level INC callbacks (registered through the CR MPI Ext interface). * Increase the {{{opal_cr_thread_sleep_wait}}} parameter to 1000 microseconds to make the C/R thread less aggressive. * {{{opal-restart}}} now looks for cache directories before falling back on stable storage when asked. * {{{opal-restart}}} also support local decompression before restarting * {{{orte-checkpoint}}} now uses the SStore framework to work with the metadata * {{{orte-restart}}} now uses the SStore framework to work with the metadata * Remove the {{{orte-restart}}} preload option. This was removed since the user only needs to select the 'stage' component in order to support this functionality. * Since the '-am' parameter is saved in the metadata, {{{ompi-restart}}} no longer hard codes {{{-am ft-enable-cr}}}. * Fix {{{hnp}}} ErrMgr so that if a previous component in the stack has 'fixed' the problem, then it should be skipped. * Make sure to decrement the number of 'num_local_procs' in the orted when one goes away. * odls now checks the SStore framework to see if it needs to load any checkpoint files before launching (to support 'stage'). This separates the SStore logic from the --preload-[binary|files] options. * Add unique IDs to the named pipes established between the orted and the app in SnapC. This is to better support migration and automatic recovery activities. * Improve the checks for 'already checkpointing' error path. * A a recovery output timer, to show how long it takes to restart a job * Do a better job of cleaning up the old session directory on restart. * Add a local module to the autor and crmig ErrMgr components. These small modules prevent the 'orted' component from attempting a local recovery (Which does not work for MPI apps at the moment) * Add a fix for bounding the checkpointable region between MPI_Init and MPI_Finalize. This commit was SVN r23587. The following Trac tickets were found above: Ticket 1924 --> https://svn.open-mpi.org/trac/ompi/ticket/1924 Ticket 2097 --> https://svn.open-mpi.org/trac/ompi/ticket/2097 Ticket 2161 --> https://svn.open-mpi.org/trac/ompi/ticket/2161 Ticket 2192 --> https://svn.open-mpi.org/trac/ompi/ticket/2192 Ticket 2208 --> https://svn.open-mpi.org/trac/ompi/ticket/2208 Ticket 2342 --> https://svn.open-mpi.org/trac/ompi/ticket/2342 Ticket 2413 --> https://svn.open-mpi.org/trac/ompi/ticket/2413
2010-08-11 00:51:11 +04:00
opal_pointer_array_add(&mca_types, "sstore");
opal_pointer_array_add(&mca_types, "snapc");
#endif
#if ORTE_ENABLE_SENSORS
opal_pointer_array_add(&mca_types, "sensor");
#endif
opal_pointer_array_add(&mca_types, "filem");
#endif
/* these are always included */
opal_pointer_array_add(&mca_types, "state");
opal_pointer_array_add(&mca_types, "errmgr");
opal_pointer_array_add(&mca_types, "ess");
opal_pointer_array_add(&mca_types, "grpcomm");
opal_pointer_array_add(&mca_types, "db");
/* Execute the desired action(s) */
if (opal_cmd_line_is_taken(ompi_info_cmd_line, "ompi_info_pretty")) {
ompi_info_pretty = true;
} else if (opal_cmd_line_is_taken(ompi_info_cmd_line, "parsable") || opal_cmd_line_is_taken(ompi_info_cmd_line, "parseable")) {
ompi_info_pretty = false;
}
want_all = opal_cmd_line_is_taken(ompi_info_cmd_line, "all");
if (want_all || opal_cmd_line_is_taken(ompi_info_cmd_line, "version")) {
ompi_info_do_version(want_all, ompi_info_cmd_line);
acted = true;
}
if (want_all || opal_cmd_line_is_taken(ompi_info_cmd_line, "path")) {
ompi_info_do_path(want_all, ompi_info_cmd_line);
acted = true;
}
if (want_all || opal_cmd_line_is_taken(ompi_info_cmd_line, "arch")) {
ompi_info_do_arch();
acted = true;
}
if (want_all || opal_cmd_line_is_taken(ompi_info_cmd_line, "hostname")) {
ompi_info_do_hostname();
acted = true;
}
if (want_all || opal_cmd_line_is_taken(ompi_info_cmd_line, "config")) {
ompi_info_do_config(true);
acted = true;
}
if (want_all || opal_cmd_line_is_taken(ompi_info_cmd_line, "param")) {
ompi_info_do_params(want_all, opal_cmd_line_is_taken(ompi_info_cmd_line, "internal"));
acted = true;
}
/* If no command line args are specified, show default set */
if (!acted) {
ompi_info_show_ompi_version(ompi_info_ver_full);
ompi_info_show_path(ompi_info_path_prefix, opal_install_dirs.prefix);
ompi_info_do_arch();
ompi_info_do_hostname();
ompi_info_do_config(false);
ompi_info_open_components();
for (i = 0; i < mca_types.size; ++i) {
if (NULL == (str = (char*)opal_pointer_array_get_item(&mca_types, i))) {
continue;
}
if (0 != strcmp("mpi", str)) {
ompi_info_show_component_version(str, ompi_info_component_all,
ompi_info_ver_full, ompi_info_type_all);
}
}
}
/* All done */
if (NULL != app_env) {
opal_argv_free(app_env);
}
if (NULL != global_env) {
opal_argv_free(global_env);
}
ompi_info_close_components();
OBJ_RELEASE(ompi_info_cmd_line);
OBJ_DESTRUCT(&mca_types);
mca_base_close();
opal_finalize_util();
return 0;
}