1
1

139 строки
5.5 KiB
C
Исходник Обычный вид История

/*
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
2010-08-10 20:51:11 +00:00
* Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2005 The University of Tennessee and The University
* of Tennessee Research Foundation. All rights
* reserved.
2015-06-23 20:59:57 -07:00
* 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) 2007 Evergrid, Inc. All rights reserved.
* Copyright (c) 2013 Los Alamos National Security, LLC. All rights reserved.
*
* $COPYRIGHT$
2015-06-23 20:59:57 -07:00
*
* Additional copyrights may follow
2015-06-23 20:59:57 -07:00
*
* $HEADER$
*/
#ifndef ORTE_SNAPC_BASE_H
#define ORTE_SNAPC_BASE_H
#include "orte_config.h"
#include "orte/types.h"
#include "orte/mca/snapc/snapc.h"
/*
* Global functions for MCA overall SNAPC
*/
BEGIN_C_DECLS
/*
* MCA Framework
*/
ORTE_DECLSPEC extern mca_base_framework_t orte_snapc_base_framework;
/* select a component */
ORTE_DECLSPEC int orte_snapc_base_select(bool seed, bool app);
/*
* Commands for command line tool and SnapC interaction
*/
typedef uint8_t orte_snapc_cmd_flag_t;
#define ORTE_SNAPC_CMD OPAL_UINT8
#define ORTE_SNAPC_GLOBAL_INIT_CMD 1
#define ORTE_SNAPC_GLOBAL_TERM_CMD 2
#define ORTE_SNAPC_GLOBAL_UPDATE_CMD 3
#define ORTE_SNAPC_LOCAL_UPDATE_CMD 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
2010-08-10 20:51:11 +00:00
#define ORTE_SNAPC_LOCAL_FINISH_CMD 5
/**
* There are 3 types of Coordinators, and any process may be once or more type.
* e.g., orterun is can often be both a Global and Local coordinator if it
* launches processes locally.
*/
typedef uint32_t orte_snapc_coord_type_t;
#define ORTE_SNAPC_UNASSIGN_TYPE 0
#define ORTE_SNAPC_GLOBAL_COORD_TYPE 1
#define ORTE_SNAPC_LOCAL_COORD_TYPE 2
#define ORTE_SNAPC_APP_COORD_TYPE 4
ORTE_DECLSPEC extern orte_snapc_coord_type_t orte_snapc_coord_type;
#define ORTE_SNAPC_COORD_NAME_PRINT(ct) ( (ct == (ORTE_SNAPC_GLOBAL_COORD_TYPE | ORTE_SNAPC_LOCAL_COORD_TYPE) ) ? "Global-Local" : \
(ct == ORTE_SNAPC_GLOBAL_COORD_TYPE) ? "Global" : \
(ct == ORTE_SNAPC_LOCAL_COORD_TYPE) ? "Local" : \
(ct == ORTE_SNAPC_APP_COORD_TYPE) ? "App" : \
"Unknown")
/**
* Global Snapshot Object Maintenance functions
*/
void orte_snapc_base_local_snapshot_construct(orte_snapc_base_local_snapshot_t *obj);
void orte_snapc_base_local_snapshot_destruct( orte_snapc_base_local_snapshot_t *obj);
void orte_snapc_base_global_snapshot_construct(orte_snapc_base_global_snapshot_t *obj);
void orte_snapc_base_global_snapshot_destruct( orte_snapc_base_global_snapshot_t *obj);
void orte_snapc_base_quiesce_construct(orte_snapc_base_quiesce_t *obj);
void orte_snapc_base_quiesce_destruct( orte_snapc_base_quiesce_t *obj);
void orte_snapc_base_request_op_construct(orte_snapc_base_request_op_t *op);
void orte_snapc_base_request_op_destruct(orte_snapc_base_request_op_t *op);
/**
* 'None' component functions
* These are to be used when no component is selected.
* They just return success, and empty strings as necessary.
*/
ORTE_DECLSPEC int orte_snapc_base_none_open(void);
ORTE_DECLSPEC int orte_snapc_base_none_close(void);
ORTE_DECLSPEC int orte_snapc_base_none_query(mca_base_module_t **module, int *priority);
ORTE_DECLSPEC int orte_snapc_base_module_init(bool seed, bool app);
ORTE_DECLSPEC int orte_snapc_base_module_finalize(void);
ORTE_DECLSPEC int orte_snapc_base_none_setup_job(orte_jobid_t jobid);
ORTE_DECLSPEC int orte_snapc_base_none_release_job(orte_jobid_t jobid);
ORTE_DECLSPEC int orte_snapc_base_none_ft_event(int state);
ORTE_DECLSPEC int orte_snapc_base_none_start_ckpt(orte_snapc_base_quiesce_t *datum);
ORTE_DECLSPEC int orte_snapc_base_none_end_ckpt(orte_snapc_base_quiesce_t *datum);
ORTE_DECLSPEC extern orte_snapc_base_module_t orte_snapc;
/**
* Globals
*/
ORTE_DECLSPEC extern bool orte_snapc_base_store_only_one_seq;
ORTE_DECLSPEC extern size_t orte_snapc_base_snapshot_seq_number;
ORTE_DECLSPEC extern bool orte_snapc_base_has_recovered;
/**
* Some utility functions
*/
ORTE_DECLSPEC void orte_snapc_ckpt_state_notify(int state);
ORTE_DECLSPEC int orte_snapc_ckpt_state_str(char ** state_str, int state);
/*******************************
* Global Coordinator functions
*******************************/
/* Initial handshake with the orte_checkpoint command */
ORTE_DECLSPEC int orte_snapc_base_global_coord_ckpt_init_cmd(orte_process_name_t* peer,
opal_buffer_t* buffer,
opal_crs_base_ckpt_options_t *options,
orte_jobid_t *jobid);
ORTE_DECLSPEC int orte_snapc_base_global_coord_ckpt_update_cmd(orte_process_name_t* peer,
orte_sstore_base_handle_t handle,
int ckpt_status);
ORTE_DECLSPEC int orte_snapc_base_unpack_options(opal_buffer_t* buffer,
opal_crs_base_ckpt_options_t *options);
ORTE_DECLSPEC int orte_snapc_base_pack_options(opal_buffer_t* buffer,
opal_crs_base_ckpt_options_t *options);
2009-09-22 18:26:12 +00:00
END_C_DECLS
#endif /* ORTE_SNAPC_BASE_H */