5406fdfb80
This commit looks larger than it really is since it includes a fair amount of code cleanup.
The SIGSTOP/SIGCONT+checkpointing work uses some of the functionality in r20391. Basic use case below (note that the checkpoint generated is useable as usual if the stopped application is terminated).
{{{
shell 1) mpirun -np 2 -am ft-enable-cr my-app
... running ...
shell 2) ompi-checkpoint --stop -v MPIRUN_PID
[localhost:001300] [ 0.00 / 0.20] Requested - ...
[localhost:001300] [ 0.00 / 0.20] Pending - ...
[localhost:001300] [ 0.01 / 0.21] Running - ...
[localhost:001300] [ 1.01 / 1.22] Stopped - ompi_global_snapshot_1234.ckpt
Snapshot Ref.: 0 ompi_global_snapshot_1234.ckpt
shell 2) killall -CONT mpirun
... Application Continues execution in shell 1 ...
}}}
Other items in this commit are mostly cleanup that has been sitting off-trunk for too long:
* Add a new {{{opal_crs_base_ckpt_options_t}}} type that encapsulates the various options that could be passed to the CRS. Currently only TERM and STOP, but this makes adding others ''much'' easier.
* Eliminate ORTE_SNAPC_CKPT_STATE_PENDING_TERM, since it served a redundant purpose with the new options type.
* Lay some basic ground work for some future features.
This commit was SVN r21995.
The following SVN revision numbers were found above:
r20391 --> open-mpi/ompi@0704b98668
97 строки
3.0 KiB
C
97 строки
3.0 KiB
C
/*
|
|
* Copyright (c) 2004-2009 The Trustees of Indiana University.
|
|
* All rights reserved.
|
|
* Copyright (c) 2004-2005 The Trustees of the University of Tennessee.
|
|
* 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.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
/**
|
|
* @file
|
|
*
|
|
* SELF CRS component
|
|
*
|
|
* Simple, braindead implementation.
|
|
*/
|
|
|
|
#ifndef MCA_CRS_SELF_EXPORT_H
|
|
#define MCA_CRS_SELF_EXPORT_H
|
|
|
|
#include "opal_config.h"
|
|
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/mca/crs/crs.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
#define PREFIX_DEFAULT ("opal_crs_self_user")
|
|
#define SUFFIX_CHECKPOINT ("checkpoint")
|
|
#define SUFFIX_CONTINUE ("continue")
|
|
#define SUFFIX_RESTART ("restart")
|
|
|
|
typedef int (*opal_crs_self_checkpoint_callback_fn_t)(char **restart_cmd);
|
|
typedef int (*opal_crs_self_continue_callback_fn_t)(void);
|
|
typedef int (*opal_crs_self_restart_callback_fn_t)(void);
|
|
|
|
/*
|
|
* Local Component structures
|
|
*/
|
|
struct opal_crs_self_component_t {
|
|
opal_crs_base_component_t super; /** Base CRS component */
|
|
|
|
char *prefix; /** Prefix for user callbacks */
|
|
bool do_restart; /** Start by calling user restart routine in opal_init? */
|
|
bool can_checkpoint; /** If checkpointing is enabled */
|
|
|
|
/** User defined functions */
|
|
opal_crs_self_checkpoint_callback_fn_t ucb_checkpoint_fn;
|
|
opal_crs_self_continue_callback_fn_t ucb_continue_fn;
|
|
opal_crs_self_restart_callback_fn_t ucb_restart_fn;
|
|
};
|
|
typedef struct opal_crs_self_component_t opal_crs_self_component_t;
|
|
OPAL_MODULE_DECLSPEC extern opal_crs_self_component_t mca_crs_self_component;
|
|
|
|
int opal_crs_self_component_query(mca_base_module_t **module, int *priority);
|
|
|
|
/*
|
|
* Module functions
|
|
*/
|
|
int opal_crs_self_module_init(void);
|
|
int opal_crs_self_module_finalize(void);
|
|
|
|
/*
|
|
* Actual funcationality
|
|
*/
|
|
int opal_crs_self_checkpoint( pid_t pid,
|
|
opal_crs_base_snapshot_t *snapshot,
|
|
opal_crs_base_ckpt_options_t *options,
|
|
opal_crs_state_type_t *state);
|
|
|
|
int opal_crs_self_restart( opal_crs_base_snapshot_t *snapshot, bool spawn_child, pid_t *child_pid);
|
|
|
|
int opal_crs_self_disable_checkpoint(void);
|
|
int opal_crs_self_enable_checkpoint(void);
|
|
|
|
int opal_crs_self_prelaunch(int32_t rank,
|
|
char *base_snapshot_dir,
|
|
char **app,
|
|
char **cwd,
|
|
char ***argv,
|
|
char ***env);
|
|
|
|
int opal_crs_self_reg_thread(void);
|
|
|
|
|
|
END_C_DECLS
|
|
|
|
#endif /* MCA_CRS_SELF_EXPORT_H */
|