1
1
openmpi/opal/mca/compress/compress.h

136 строки
3.5 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
2010-08-11 00:51:11 +04:00
/*
* Copyright (c) 2004-2010 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
*
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/**
* @file
*
* Compression Framework
*
* General Description:
*
* The OPAL Compress framework has been created to provide an abstract interface
* to the compression agent library on the host machine. This fromework is useful
* when distributing files that can be compressed before sending to dimish the
* load on the network.
*
*/
#ifndef MCA_COMPRESS_H
#define MCA_COMPRESS_H
#include "opal_config.h"
#include "opal/mca/mca.h"
#include "opal/mca/base/base.h"
#include "opal/class/opal_object.h"
#if defined(c_plusplus) || defined(__cplusplus)
extern "C" {
#endif
/**
* Module initialization function.
* Returns OPAL_SUCCESS
*/
typedef int (*opal_compress_base_module_init_fn_t)
(void);
/**
* Module finalization function.
* Returns OPAL_SUCCESS
*/
typedef int (*opal_compress_base_module_finalize_fn_t)
(void);
/**
* Compress the file provided
*
* Arguments:
* fname = Filename to compress
* cname = Compressed filename
* postfix = postfix added to filename to create compressed filename
* Returns:
* OPAL_SUCCESS on success, ow OPAL_ERROR
*/
typedef int (*opal_compress_base_module_compress_fn_t)
(char * fname, char **cname, char **postfix);
typedef int (*opal_compress_base_module_compress_nb_fn_t)
(char * fname, char **cname, char **postfix, pid_t *child_pid);
/**
* Decompress the file provided
*
* Arguments:
* fname = Filename to compress
* cname = Compressed filename
* Returns:
* OPAL_SUCCESS on success, ow OPAL_ERROR
*/
typedef int (*opal_compress_base_module_decompress_fn_t)
(char * cname, char **fname);
typedef int (*opal_compress_base_module_decompress_nb_fn_t)
(char * cname, char **fname, pid_t *child_pid);
/**
* Structure for COMPRESS components.
*/
struct opal_compress_base_component_2_0_0_t {
/** MCA base component */
mca_base_component_t base_version;
/** MCA base data */
mca_base_component_data_t base_data;
/** Verbosity Level */
int verbose;
/** Output Handle for opal_output */
int output_handle;
/** Default Priority */
int priority;
};
typedef struct opal_compress_base_component_2_0_0_t opal_compress_base_component_2_0_0_t;
typedef struct opal_compress_base_component_2_0_0_t opal_compress_base_component_t;
/**
* Structure for COMPRESS modules
*/
struct opal_compress_base_module_1_0_0_t {
/** Initialization Function */
opal_compress_base_module_init_fn_t init;
/** Finalization Function */
opal_compress_base_module_finalize_fn_t finalize;
/** Compress interface */
opal_compress_base_module_compress_fn_t compress;
opal_compress_base_module_compress_nb_fn_t compress_nb;
/** Decompress Interface */
opal_compress_base_module_decompress_fn_t decompress;
opal_compress_base_module_decompress_nb_fn_t decompress_nb;
};
typedef struct opal_compress_base_module_1_0_0_t opal_compress_base_module_1_0_0_t;
typedef struct opal_compress_base_module_1_0_0_t opal_compress_base_module_t;
OPAL_DECLSPEC extern opal_compress_base_module_t opal_compress;
/**
* Macro for use in components that are of type COMPRESS
*/
#define OPAL_COMPRESS_BASE_VERSION_2_0_0 \
MCA_BASE_VERSION_2_0_0, \
"compress", 2, 0, 0
#if defined(c_plusplus) || defined(__cplusplus)
}
#endif
#endif /* OPAL_COMPRESS_H */