1
1
openmpi/ompi/runtime/ompi_cr.c

508 строки
15 KiB
C
Исходник Обычный вид История

/* -*- Mode: C; c-basic-offset:4 ; -*- */
/*
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
* Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2011 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) 2012 The University of Wisconsin-La Crosse. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/** @file
*
* OMPI Layer Checkpoint/Restart Runtime functions
*
*/
#include "ompi_config.h"
#include <errno.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif /* HAVE_UNISTD_H */
#ifdef HAVE_FCNTL_H
#include <fcntl.h>
#endif /* HAVE_FCNTL_H */
#ifdef HAVE_SYS_TYPES_H
#include <sys/types.h>
#endif /* HAVE_SYS_TYPES_H */
#ifdef HAVE_SYS_STAT_H
#include <sys/stat.h> /* for mkfifo */
#endif /* HAVE_SYS_STAT_H */
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
#include "opal/mca/event/event.h"
#include "opal/util/output.h"
#include "opal/mca/crs/crs.h"
#include "opal/mca/crs/base/base.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
#include "opal/mca/installdirs/installdirs.h"
#include "opal/runtime/opal_cr.h"
#if OPAL_ENABLE_FT_CR == 1
#include "orte/mca/snapc/snapc.h"
#include "orte/mca/snapc/base/base.h"
#endif
#include "ompi/constants.h"
#include "ompi/mca/pml/pml.h"
#include "ompi/mca/pml/base/base.h"
#include "ompi/mca/btl/base/base.h"
#include "ompi/mca/crcp/crcp.h"
#include "ompi/mca/crcp/base/base.h"
#include "ompi/communicator/communicator.h"
#include "ompi/runtime/ompi_cr.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_CRDEBUG == 1
#include "ompi/debuggers/debuggers.h"
#endif
#if OPAL_ENABLE_CRDEBUG == 1
OMPI_DECLSPEC int MPIR_checkpointable = 0;
OMPI_DECLSPEC char * MPIR_controller_hostname = NULL;
OMPI_DECLSPEC char * MPIR_checkpoint_command = NULL;
OMPI_DECLSPEC char * MPIR_restart_command = NULL;
OMPI_DECLSPEC char * MPIR_checkpoint_listing_command = NULL;
#endif
/*************
* Local functions
*************/
static int ompi_cr_coord_pre_ckpt(void);
static int ompi_cr_coord_pre_restart(void);
static int ompi_cr_coord_pre_continue(void);
static int ompi_cr_coord_post_ckpt(void);
static int ompi_cr_coord_post_restart(void);
static int ompi_cr_coord_post_continue(void);
/*************
* Local vars
*************/
static opal_cr_coord_callback_fn_t prev_coord_callback = NULL;
int ompi_cr_output = -1;
#define NUM_COLLECTIVES 16
#define SIGNAL(comm, modules, highest_module, msg, ret, func) \
do { \
bool found = false; \
int k; \
mca_coll_base_module_t *my_module = \
comm->c_coll.coll_ ## func ## _module; \
if (NULL != my_module) { \
for (k = 0 ; k < highest_module ; ++k) { \
if (my_module == modules[k]) found = true; \
} \
if (!found) { \
modules[highest_module++] = my_module; \
if (NULL != my_module->ft_event) { \
ret = my_module->ft_event(msg); \
if( OMPI_SUCCESS != ret ) { \
return ret; \
} \
} \
} \
} \
} while (0)
static int
notify_collectives(int msg)
{
mca_coll_base_module_t *modules[NUM_COLLECTIVES];
int i, max, ret, highest_module = 0;
memset(&modules, 0, sizeof(mca_coll_base_module_t*) * NUM_COLLECTIVES);
max = opal_pointer_array_get_size(&ompi_mpi_communicators);
for (i = 0 ; i < max ; ++i) {
ompi_communicator_t *comm =
(ompi_communicator_t *)opal_pointer_array_get_item(&ompi_mpi_communicators, i);
if (NULL == comm) continue;
SIGNAL(comm, modules, highest_module, msg, ret, allgather);
SIGNAL(comm, modules, highest_module, msg, ret, allgatherv);
SIGNAL(comm, modules, highest_module, msg, ret, allreduce);
SIGNAL(comm, modules, highest_module, msg, ret, alltoall);
SIGNAL(comm, modules, highest_module, msg, ret, alltoallv);
SIGNAL(comm, modules, highest_module, msg, ret, alltoallw);
SIGNAL(comm, modules, highest_module, msg, ret, barrier);
SIGNAL(comm, modules, highest_module, msg, ret, bcast);
SIGNAL(comm, modules, highest_module, msg, ret, exscan);
SIGNAL(comm, modules, highest_module, msg, ret, gather);
SIGNAL(comm, modules, highest_module, msg, ret, gatherv);
SIGNAL(comm, modules, highest_module, msg, ret, reduce);
SIGNAL(comm, modules, highest_module, msg, ret, reduce_scatter);
SIGNAL(comm, modules, highest_module, msg, ret, scan);
SIGNAL(comm, modules, highest_module, msg, ret, scatter);
SIGNAL(comm, modules, highest_module, msg, ret, scatterv);
}
return OMPI_SUCCESS;
}
/*
* CR Init
*/
int ompi_cr_init(void)
{
int val;
/*
* Register some MCA parameters
*/
mca_base_param_reg_int_name("ompi_cr", "verbose",
"Verbose output for the OMPI Checkpoint/Restart functionality",
false, false,
0,
&val);
if(0 != val) {
ompi_cr_output = opal_output_open(NULL);
opal_output_set_verbosity(ompi_cr_output, val);
} else {
ompi_cr_output = opal_cr_output;
}
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: init: ompi_cr_init()");
/* Register the OMPI interlevel coordination callback */
opal_cr_reg_coord_callback(ompi_cr_coord, &prev_coord_callback);
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_CRDEBUG == 1
/* Check for C/R enabled debugging */
if( MPIR_debug_with_checkpoint ) {
char *uri = NULL;
char *sep = NULL;
char *hostname = NULL;
/* Mark as debuggable with C/R */
MPIR_checkpointable = 1;
/* Set the checkpoint and restart commands */
/* Add the full path to the binary */
asprintf(&MPIR_checkpoint_command,
"%s/ompi-checkpoint --crdebug --hnp-jobid %u",
opal_install_dirs.bindir,
ORTE_PROC_MY_HNP->jobid);
asprintf(&MPIR_restart_command,
"%s/ompi-restart --crdebug ",
opal_install_dirs.bindir);
asprintf(&MPIR_checkpoint_listing_command,
"%s/ompi-checkpoint -l --crdebug ",
opal_install_dirs.bindir);
/* Set contact information for HNP */
uri = strdup(ompi_process_info.my_hnp_uri);
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
hostname = strchr(uri, ';') + 1;
sep = strchr(hostname, ';');
if (sep) {
*sep = 0;
}
if (strncmp(hostname, "tcp://", 6) == 0) {
hostname += 6;
sep = strchr(hostname, ':');
*sep = 0;
MPIR_controller_hostname = strdup(hostname);
} else {
MPIR_controller_hostname = strdup("localhost");
}
/* Cleanup */
if( NULL != uri ) {
free(uri);
uri = NULL;
}
}
#endif
return OMPI_SUCCESS;
}
/*
* Finalize
*/
int ompi_cr_finalize(void)
{
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: finalize: ompi_cr_finalize()");
return OMPI_SUCCESS;
}
/*
* Interlayer coordination callback
*/
int ompi_cr_coord(int state)
{
int ret, exit_status = OMPI_SUCCESS;
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: coord: ompi_cr_coord(%s)\n",
opal_crs_base_state_str((opal_crs_state_type_t)state));
/*
* Before calling the previous callback, we have the opportunity to
* take action given the state.
*/
if(OPAL_CRS_CHECKPOINT == state) {
/* Do Checkpoint Phase work */
ret = ompi_cr_coord_pre_ckpt();
if( ret == OMPI_EXISTS) {
return ret;
}
else if( ret != OMPI_SUCCESS) {
return ret;
}
}
else if (OPAL_CRS_CONTINUE == state ) {
/* Do Continue Phase work */
ompi_cr_coord_pre_continue();
}
else if (OPAL_CRS_RESTART == state ) {
/* Do Restart Phase work */
ompi_cr_coord_pre_restart();
}
else if (OPAL_CRS_TERM == state ) {
/* Do Continue Phase work in prep to terminate the application */
}
else {
/* We must have been in an error state from the checkpoint
* recreate everything, as in the Continue Phase
*/
}
/*
* Call the previous callback, which should be ORTE [which will handle OPAL]
*/
if(OMPI_SUCCESS != (ret = prev_coord_callback(state)) ) {
exit_status = ret;
goto cleanup;
}
/*
* After calling the previous callback, we have the opportunity to
* take action given the state to tidy up.
*/
if(OPAL_CRS_CHECKPOINT == state) {
/* Do Checkpoint Phase work */
ompi_cr_coord_post_ckpt();
}
else if (OPAL_CRS_CONTINUE == state ) {
/* Do Continue Phase work */
ompi_cr_coord_post_continue();
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_CRDEBUG == 1
/*
* If C/R enabled debugging,
* wait here for debugger to attach
*/
if( MPIR_debug_with_checkpoint ) {
MPIR_checkpoint_debugger_breakpoint();
}
#endif
}
else if (OPAL_CRS_RESTART == state ) {
/* Do Restart Phase work */
ompi_cr_coord_post_restart();
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_CRDEBUG == 1
/*
* If C/R enabled debugging,
* wait here for debugger to attach
*/
if( MPIR_debug_with_checkpoint ) {
MPIR_checkpoint_debugger_breakpoint();
}
#endif
}
else if (OPAL_CRS_TERM == state ) {
/* Do Continue Phase work in prep to terminate the application */
}
else {
/* We must have been in an error state from the checkpoint
* recreate everything, as in the Continue Phase
*/
}
cleanup:
return exit_status;
}
/*************
* Pre Lower Layer
*************/
static int ompi_cr_coord_pre_ckpt(void) {
int ret, exit_status = OMPI_SUCCESS;
/*
* All the checkpoint heavey lifting in here...
*/
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: coord_pre_ckpt: ompi_cr_coord_pre_ckpt()\n");
/*
* Notify Collectives
* - Need to do this on a per communicator basis
* Traverse all communicators...
*/
if (OMPI_SUCCESS != (ret = notify_collectives(OPAL_CR_CHECKPOINT))) {
goto cleanup;
}
/*
* Notify PML
* - Will notify BML and BTL's
*/
if( OMPI_SUCCESS != (ret = mca_pml.pml_ft_event(OPAL_CRS_CHECKPOINT))) {
exit_status = ret;
goto cleanup;
}
cleanup:
return exit_status;
}
static int ompi_cr_coord_pre_restart(void) {
Fix a checkpoint/restart bug that causes a restarted application to occasionally throw a SIGSEGV or SIGPIPE due to invalid socket descriptors. The problem was caused by a bad ordering between the restart of the ORTE level tcp connections (in the OOB - out-of-band communication) and the Open MPI level tcp connections (BTLs). Before this commit ORTE would shutdown and restart the OOB completely before the OMPI level restarted its tcp connections. What would happen is that a socket descriptor used by the OMPI level on checkpoint was assigned to the ORTE level on restart. But the OMPI level had no knowledge that the socket descriptor it was previously using has been recycled so it closed it on restart. This caused the ORTE level to break as the newly created socket descriptor was closed without its knowledge. The fix is to have the OMPI level shutdown tcp connections, allow the ORTE level to restart, and then allow the OMPi level to restart its connections. This seems obvious, and I'm surprised that this bug has not cropped up sooner. I'm confident that this specific problem has been fixed with this commit. Thanks to Eric Roman and Tamer El Sayed for their help in identifying this problem, and patience while I was fixing it. * Add a new state {{{OPAL_CRS_RESTART_PRE}}}. This state identifies when we are on the down slope of the INC (finalize-like) which is useful when you want to close, but not reopen a component set for fear of interfering with a lower level. * Use this new state in OMPI level coordination. Here we want to make sure to play well with both the OMPI/BTL/TCP and ORTE/OOB/TCP components. * Update ft_event functions in PML and BML to handle the new restart state. * Add an additional flag to the error output in OOB/TCP so we can see what the socket descriptor was on failure as this can be helpful in debugging. This commit was SVN r18276.
2008-04-24 21:54:22 +04:00
int ret, exit_status = OMPI_SUCCESS;
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: coord_pre_restart: ompi_cr_coord_pre_restart()");
Fix a checkpoint/restart bug that causes a restarted application to occasionally throw a SIGSEGV or SIGPIPE due to invalid socket descriptors. The problem was caused by a bad ordering between the restart of the ORTE level tcp connections (in the OOB - out-of-band communication) and the Open MPI level tcp connections (BTLs). Before this commit ORTE would shutdown and restart the OOB completely before the OMPI level restarted its tcp connections. What would happen is that a socket descriptor used by the OMPI level on checkpoint was assigned to the ORTE level on restart. But the OMPI level had no knowledge that the socket descriptor it was previously using has been recycled so it closed it on restart. This caused the ORTE level to break as the newly created socket descriptor was closed without its knowledge. The fix is to have the OMPI level shutdown tcp connections, allow the ORTE level to restart, and then allow the OMPi level to restart its connections. This seems obvious, and I'm surprised that this bug has not cropped up sooner. I'm confident that this specific problem has been fixed with this commit. Thanks to Eric Roman and Tamer El Sayed for their help in identifying this problem, and patience while I was fixing it. * Add a new state {{{OPAL_CRS_RESTART_PRE}}}. This state identifies when we are on the down slope of the INC (finalize-like) which is useful when you want to close, but not reopen a component set for fear of interfering with a lower level. * Use this new state in OMPI level coordination. Here we want to make sure to play well with both the OMPI/BTL/TCP and ORTE/OOB/TCP components. * Update ft_event functions in PML and BML to handle the new restart state. * Add an additional flag to the error output in OOB/TCP so we can see what the socket descriptor was on failure as this can be helpful in debugging. This commit was SVN r18276.
2008-04-24 21:54:22 +04:00
/*
* Notify PML
* - Will notify BML and BTL's
* - The intention here is to have the PML shutdown all the old components
* and handles. On the second pass (once ORTE is restarted) we can
Fix a checkpoint/restart bug that causes a restarted application to occasionally throw a SIGSEGV or SIGPIPE due to invalid socket descriptors. The problem was caused by a bad ordering between the restart of the ORTE level tcp connections (in the OOB - out-of-band communication) and the Open MPI level tcp connections (BTLs). Before this commit ORTE would shutdown and restart the OOB completely before the OMPI level restarted its tcp connections. What would happen is that a socket descriptor used by the OMPI level on checkpoint was assigned to the ORTE level on restart. But the OMPI level had no knowledge that the socket descriptor it was previously using has been recycled so it closed it on restart. This caused the ORTE level to break as the newly created socket descriptor was closed without its knowledge. The fix is to have the OMPI level shutdown tcp connections, allow the ORTE level to restart, and then allow the OMPi level to restart its connections. This seems obvious, and I'm surprised that this bug has not cropped up sooner. I'm confident that this specific problem has been fixed with this commit. Thanks to Eric Roman and Tamer El Sayed for their help in identifying this problem, and patience while I was fixing it. * Add a new state {{{OPAL_CRS_RESTART_PRE}}}. This state identifies when we are on the down slope of the INC (finalize-like) which is useful when you want to close, but not reopen a component set for fear of interfering with a lower level. * Use this new state in OMPI level coordination. Here we want to make sure to play well with both the OMPI/BTL/TCP and ORTE/OOB/TCP components. * Update ft_event functions in PML and BML to handle the new restart state. * Add an additional flag to the error output in OOB/TCP so we can see what the socket descriptor was on failure as this can be helpful in debugging. This commit was SVN r18276.
2008-04-24 21:54:22 +04:00
* reconnect processes.
*/
if( OMPI_SUCCESS != (ret = mca_pml.pml_ft_event(OPAL_CRS_RESTART_PRE))) {
Fix a checkpoint/restart bug that causes a restarted application to occasionally throw a SIGSEGV or SIGPIPE due to invalid socket descriptors. The problem was caused by a bad ordering between the restart of the ORTE level tcp connections (in the OOB - out-of-band communication) and the Open MPI level tcp connections (BTLs). Before this commit ORTE would shutdown and restart the OOB completely before the OMPI level restarted its tcp connections. What would happen is that a socket descriptor used by the OMPI level on checkpoint was assigned to the ORTE level on restart. But the OMPI level had no knowledge that the socket descriptor it was previously using has been recycled so it closed it on restart. This caused the ORTE level to break as the newly created socket descriptor was closed without its knowledge. The fix is to have the OMPI level shutdown tcp connections, allow the ORTE level to restart, and then allow the OMPi level to restart its connections. This seems obvious, and I'm surprised that this bug has not cropped up sooner. I'm confident that this specific problem has been fixed with this commit. Thanks to Eric Roman and Tamer El Sayed for their help in identifying this problem, and patience while I was fixing it. * Add a new state {{{OPAL_CRS_RESTART_PRE}}}. This state identifies when we are on the down slope of the INC (finalize-like) which is useful when you want to close, but not reopen a component set for fear of interfering with a lower level. * Use this new state in OMPI level coordination. Here we want to make sure to play well with both the OMPI/BTL/TCP and ORTE/OOB/TCP components. * Update ft_event functions in PML and BML to handle the new restart state. * Add an additional flag to the error output in OOB/TCP so we can see what the socket descriptor was on failure as this can be helpful in debugging. This commit was SVN r18276.
2008-04-24 21:54:22 +04:00
exit_status = ret;
goto cleanup;
}
cleanup:
return exit_status;
}
static int ompi_cr_coord_pre_continue(void) {
#if OPAL_ENABLE_FT_CR == 1
int ret, exit_status = OMPI_SUCCESS;
/*
* Can not really do much until ORTE is up and running,
* so defer action until the post_continue function.
*/
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: coord_pre_continue: ompi_cr_coord_pre_continue()");
if( orte_cr_continue_like_restart ) {
/* Mimic ompi_cr_coord_pre_restart(); */
if( OMPI_SUCCESS != (ret = mca_pml.pml_ft_event(OPAL_CRS_CONTINUE))) {
exit_status = ret;
goto cleanup;
}
}
else {
if( opal_cr_timing_barrier_enabled ) {
OPAL_CR_SET_TIMER(OPAL_CR_TIMER_P2PBR1);
}
OPAL_CR_SET_TIMER(OPAL_CR_TIMER_P2P3);
if( opal_cr_timing_barrier_enabled ) {
OPAL_CR_SET_TIMER(OPAL_CR_TIMER_P2PBR2);
}
OPAL_CR_SET_TIMER(OPAL_CR_TIMER_CRCP1);
}
cleanup:
return exit_status;
#else
return OMPI_SUCCESS;
#endif
}
/*************
* Post Lower Layer
*************/
static int ompi_cr_coord_post_ckpt(void) {
/*
* Now that ORTE/OPAL are shutdown, we really can't do much
* so assume pre_ckpt took care of everything.
*/
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: coord_post_ckpt: ompi_cr_coord_post_ckpt()");
return OMPI_SUCCESS;
}
static int ompi_cr_coord_post_restart(void) {
int ret, exit_status = OMPI_SUCCESS;
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: coord_post_restart: ompi_cr_coord_post_restart()");
/*
* Notify PML
* - Will notify BML and BTL's
*/
if( OMPI_SUCCESS != (ret = mca_pml.pml_ft_event(OPAL_CRS_RESTART))) {
exit_status = ret;
goto cleanup;
}
/*
* Notify Collectives
* - Need to do this on a per communicator basis
* Traverse all communicators...
*/
if (OMPI_SUCCESS != (ret = notify_collectives(OPAL_CRS_RESTART))) {
goto cleanup;
}
cleanup:
return exit_status;
}
static int ompi_cr_coord_post_continue(void) {
int ret, exit_status = OMPI_SUCCESS;
opal_output_verbose(10, ompi_cr_output,
"ompi_cr: coord_post_continue: ompi_cr_coord_post_continue()");
/*
* Notify PML
* - Will notify BML and BTL's
*/
if( OMPI_SUCCESS != (ret = mca_pml.pml_ft_event(OPAL_CRS_CONTINUE))) {
exit_status = ret;
goto cleanup;
}
/*
* Notify Collectives
* - Need to do this on a per communicator basis
* Traverse all communicators...
*/
if (OMPI_SUCCESS != (ret = notify_collectives(OPAL_CRS_CONTINUE))) {
goto cleanup;
}
cleanup:
return exit_status;
}