
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
303 строки
11 KiB
C
303 строки
11 KiB
C
/*
|
|
* Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2007 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) 2004-2006 The Regents of the University of California.
|
|
* All rights reserved.
|
|
* Copyright (c) 2007 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
* Copyright (c) 2008 Cisco Systems, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "ompi_config.h"
|
|
#include "opal/util/output.h"
|
|
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
#include "ompi/runtime/ompi_cr.h"
|
|
#include "ompi/mca/bml/base/base.h"
|
|
#include "ompi/mca/btl/base/base.h"
|
|
#include "ompi/mca/bml/base/bml_base_btl.h"
|
|
#include "ompi/mca/pml/base/base.h"
|
|
#include "orte/mca/grpcomm/grpcomm.h"
|
|
#include "ompi/proc/proc.h"
|
|
|
|
#include "bml_r2.h"
|
|
#include "bml_r2_ft.h"
|
|
|
|
int mca_bml_r2_ft_event(int state)
|
|
{
|
|
static bool first_continue_pass = false;
|
|
ompi_proc_t** procs = NULL;
|
|
size_t num_procs;
|
|
size_t btl_idx;
|
|
int ret, p;
|
|
int loc_state;
|
|
int param_type = -1;
|
|
char *param_list = NULL;
|
|
|
|
if(OPAL_CRS_CHECKPOINT == state) {
|
|
/* Do nothing for now */
|
|
}
|
|
else if(OPAL_CRS_CONTINUE == state) {
|
|
first_continue_pass = !first_continue_pass;
|
|
|
|
/* Since nothing in Checkpoint, we are fine here (unless required by BTL) */
|
|
if( orte_cr_continue_like_restart && !first_continue_pass) {
|
|
procs = ompi_proc_all(&num_procs);
|
|
if(NULL == procs) {
|
|
return OMPI_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
}
|
|
}
|
|
else if(OPAL_CRS_RESTART_PRE == state ) {
|
|
/* Nothing here */
|
|
}
|
|
else if(OPAL_CRS_RESTART == state ) {
|
|
procs = ompi_proc_all(&num_procs);
|
|
if(NULL == procs) {
|
|
return OMPI_ERR_OUT_OF_RESOURCE;
|
|
}
|
|
}
|
|
else if(OPAL_CRS_TERM == state ) {
|
|
;
|
|
}
|
|
else {
|
|
;
|
|
}
|
|
|
|
/* Never call the ft_event functions attached to the BTLs on the second
|
|
* pass of RESTART since on the first pass they were unloaded and therefore
|
|
* no longer exist.
|
|
*/
|
|
if( OPAL_CRS_RESTART != state ) {
|
|
if( OPAL_CRS_CONTINUE == state && !first_continue_pass ) {
|
|
;
|
|
} else {
|
|
/* Since we only ever call into the BTLs once during the first restart
|
|
* pass, just lie to them on this pass for a bit of local clarity.
|
|
*/
|
|
if( OPAL_CRS_RESTART_PRE == state ) {
|
|
loc_state = OPAL_CRS_RESTART;
|
|
} else {
|
|
loc_state = state;
|
|
}
|
|
|
|
/*
|
|
* Call ft_event in:
|
|
* - BTL modules
|
|
* - MPool modules
|
|
*
|
|
* These should be cleaning out stale state, and memory references in
|
|
* preparation for being shut down.
|
|
*/
|
|
for(btl_idx = 0; btl_idx < mca_bml_r2.num_btl_modules; btl_idx++) {
|
|
/*
|
|
* Notify Mpool
|
|
*/
|
|
if( NULL != (mca_bml_r2.btl_modules[btl_idx])->btl_mpool &&
|
|
NULL != (mca_bml_r2.btl_modules[btl_idx])->btl_mpool->mpool_ft_event ) {
|
|
opal_output_verbose(10, ompi_cr_output,
|
|
"bml:r2: ft_event: Notify the %s MPool.\n",
|
|
(mca_bml_r2.btl_modules[btl_idx])->btl_mpool->mpool_component->mpool_version.mca_component_name);
|
|
if(OMPI_SUCCESS != (ret = (mca_bml_r2.btl_modules[btl_idx])->btl_mpool->mpool_ft_event(loc_state) ) ) {
|
|
continue;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Notify BTL
|
|
*/
|
|
if( NULL != (mca_bml_r2.btl_modules[btl_idx])->btl_ft_event) {
|
|
opal_output_verbose(10, ompi_cr_output,
|
|
"bml:r2: ft_event: Notify the %s BTL.\n",
|
|
(mca_bml_r2.btl_modules[btl_idx])->btl_component->btl_version.mca_component_name);
|
|
if(OMPI_SUCCESS != (ret = (mca_bml_r2.btl_modules[btl_idx])->btl_ft_event(loc_state) ) ) {
|
|
continue;
|
|
}
|
|
}
|
|
}
|
|
} /* OPAL_CRS_CONTINUE == state && !first_continue_pass */
|
|
}
|
|
|
|
if(OPAL_CRS_CHECKPOINT == state) {
|
|
;
|
|
}
|
|
else if(OPAL_CRS_CONTINUE == state) {
|
|
/* Matches OPAL_CRS_RESTART_PRE */
|
|
if( orte_cr_continue_like_restart && first_continue_pass) {
|
|
if( OMPI_SUCCESS != (ret = mca_bml_r2_finalize()) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to finalize BML framework\n");
|
|
return ret;
|
|
}
|
|
if( OMPI_SUCCESS != (ret = mca_btl_base_close()) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to close BTL framework\n");
|
|
return ret;
|
|
}
|
|
}
|
|
/* Matches OPAL_CRS_RESTART */
|
|
else if( orte_cr_continue_like_restart && !first_continue_pass ) {
|
|
/*
|
|
* Barrier to make all processes have been successfully restarted before
|
|
* we try to remove some restart only files.
|
|
*/
|
|
if (OMPI_SUCCESS != (ret = orte_grpcomm.barrier())) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed in orte_grpcomm.barrier (%d)", ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Re-open the BTL framework to get the full list of components.
|
|
*/
|
|
if( OMPI_SUCCESS != (ret = mca_btl_base_open()) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to open BTL framework\n");
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Re-select the BTL components/modules
|
|
* This will cause the BTL components to discover the available
|
|
* network options on this machine, and post proper modex informaiton.
|
|
*/
|
|
if( OMPI_SUCCESS != (ret = mca_btl_base_select(OPAL_ENABLE_PROGRESS_THREADS,
|
|
OMPI_ENABLE_THREAD_MULTIPLE) ) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to select in BTL framework\n");
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Clear some structures so we can properly repopulate them
|
|
*/
|
|
mca_bml_r2.btls_added = false;
|
|
|
|
for(p = 0; p < (int)num_procs; ++p) {
|
|
if( NULL != procs[p]->proc_bml) {
|
|
OBJ_RELEASE(procs[p]->proc_bml);
|
|
procs[p]->proc_bml = NULL;
|
|
}
|
|
|
|
OBJ_RELEASE(procs[p]);
|
|
}
|
|
|
|
if( NULL != procs ) {
|
|
free(procs);
|
|
procs = NULL;
|
|
}
|
|
}
|
|
}
|
|
else if(OPAL_CRS_RESTART_PRE == state ) {
|
|
opal_output_verbose(10, ompi_cr_output,
|
|
"bml:r2: ft_event(Restart): Finalize BML\n");
|
|
|
|
/*
|
|
* Finalize the BML
|
|
* - Flush progress functions
|
|
* - Flush module references
|
|
* - mca_btl_base_close()
|
|
* Need to do this because we may have BTL components that were
|
|
* unloaded in the first selection that may be available now.
|
|
* Conversely we may have BTL components loaded now that
|
|
* are not available now.
|
|
*/
|
|
if( OMPI_SUCCESS != (ret = mca_bml_r2_finalize()) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to finalize BML framework\n");
|
|
return ret;
|
|
}
|
|
if( OMPI_SUCCESS != (ret = mca_btl_base_close()) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to close BTL framework\n");
|
|
return ret;
|
|
}
|
|
}
|
|
else if(OPAL_CRS_RESTART == state ) {
|
|
|
|
/*
|
|
* Barrier to make all processes have been successfully restarted before
|
|
* we try to remove some restart only files.
|
|
*/
|
|
if (OMPI_SUCCESS != (ret = orte_grpcomm.barrier())) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed in orte_grpcomm.barrier (%d)", ret);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Re-open the BTL framework to get the full list of components.
|
|
* - but first clear the MCA value that was there
|
|
*/
|
|
param_type = mca_base_param_find("btl", NULL, NULL);
|
|
mca_base_param_lookup_string(param_type, ¶m_list);
|
|
opal_output_verbose(11, ompi_cr_output,
|
|
"Restart (Previous BTL MCA): <%s>\n", param_list);
|
|
if( NULL != param_list ) {
|
|
free(param_list);
|
|
param_list = NULL;
|
|
}
|
|
|
|
/* Deregister the old value, and refresh the file cache to grab any updates */
|
|
mca_base_param_deregister(param_type);
|
|
mca_base_param_recache_files(false);
|
|
|
|
if( OMPI_SUCCESS != (ret = mca_btl_base_open()) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to open BTL framework\n");
|
|
return ret;
|
|
}
|
|
|
|
param_type = mca_base_param_find("btl", NULL, NULL);
|
|
mca_base_param_lookup_string(param_type, ¶m_list);
|
|
opal_output_verbose(11, ompi_cr_output,
|
|
"Restart (New BTL MCA): <%s>\n", param_list);
|
|
if( NULL != param_list ) {
|
|
free(param_list);
|
|
param_list = NULL;
|
|
}
|
|
|
|
/*
|
|
* Re-select the BTL components/modules
|
|
* This will cause the BTL components to discover the available
|
|
* network options on this machine, and post proper modex informaiton.
|
|
*/
|
|
if( OMPI_SUCCESS != (ret = mca_btl_base_select(OPAL_ENABLE_PROGRESS_THREADS,
|
|
OMPI_ENABLE_THREAD_MULTIPLE) ) ) {
|
|
opal_output(0, "bml:r2: ft_event(Restart): Failed to select in BTL framework\n");
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Clear some structures so we can properly repopulate them
|
|
*/
|
|
mca_bml_r2.btls_added = false;
|
|
|
|
for(p = 0; p < (int)num_procs; ++p) {
|
|
if( NULL != procs[p]->proc_bml) {
|
|
OBJ_RELEASE(procs[p]->proc_bml);
|
|
procs[p]->proc_bml = NULL;
|
|
}
|
|
|
|
OBJ_RELEASE(procs[p]);
|
|
}
|
|
|
|
if( NULL != procs ) {
|
|
free(procs);
|
|
procs = NULL;
|
|
}
|
|
}
|
|
else if(OPAL_CRS_TERM == state ) {
|
|
;
|
|
}
|
|
else {
|
|
;
|
|
}
|
|
|
|
return OMPI_SUCCESS;
|
|
}
|