1
1
openmpi/orte/mca/ess/alps/ess_alps_module.c
Josh Hursey 3b4073e32c This commit fixes the checkpoint/restart functionality on the trunk. Included in this commit are:
* Extension to the ESS framework to support C/R
 * Fixed support for {{{snapc_base_establish_global_snapshot_dir}}}
 * Fixed FileM support
 * Misc. minor code modifications

There are some outstanding visability issues that I want to fix next.

This commit was SVN r17725.
2008-03-05 04:57:23 +00:00

166 строки
4.7 KiB
C

/*
* Copyright (c) 2004-2005 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.
* 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
*
* $HEADER$
*
*/
#include "orte_config.h"
#include "orte/constants.h"
#include <catamount/cnos_mpi_os.h>
#include "opal/util/show_help.h"
#include "orte/util/proc_info.h"
#include "orte/mca/errmgr/base/base.h"
#include "orte/util/name_fns.h"
#include "orte/runtime/orte_globals.h"
#include "orte/mca/ess/ess.h"
#include "orte/mca/ess/base/base.h"
#include "orte/mca/ess/alps/ess_alps.h"
static int alps_set_name(void);
static int rte_init(char flags);
static int rte_finalize(void);
orte_ess_base_module_t orte_ess_alps_module = {
rte_init,
rte_finalize,
orte_ess_base_app_abort,
NULL /* ft_event */
};
static int rte_init(char flags)
{
int ret;
char *error = NULL;
/* Start by getting a unique name */
alps_set_name();
/* if I am a daemon, complete my setup using the
* default procedure
*/
if (orte_process_info.daemon) {
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_setup())) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_orted_setup";
goto error;
}
} else if (orte_process_info.tool) {
/* otherwise, if I am a tool proc, use that procedure */
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_setup())) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_tool_setup";
goto error;
}
} else {
/* otherwise, I must be an application process, so
* use that default procedure
*/
if (ORTE_SUCCESS != (ret = orte_ess_base_app_setup())) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_app_setup";
goto error;
}
}
return ORTE_SUCCESS;
error:
opal_show_help("help-orte-runtime.txt",
"orte_init:startup:internal-failure",
true, error, ORTE_ERROR_NAME(ret), ret);
return ret;
}
static int rte_finalize(void)
{
int ret;
/* if I am a daemon, finalize using the default procedure */
if (orte_process_info.daemon) {
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_finalize())) {
ORTE_ERROR_LOG(ret);
}
} else if (orte_process_info.tool) {
/* otherwise, if I am a tool proc, use that procedure */
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_finalize())) {
ORTE_ERROR_LOG(ret);
}
} else {
/* otherwise, I must be an application process, so
* use that default procedure
*/
if (ORTE_SUCCESS != (ret = orte_ess_base_app_finalize())) {
ORTE_ERROR_LOG(ret);
}
}
return ret;
}
static int alps_set_name(void)
{
int rc;
int id;
orte_jobid_t jobid;
orte_vpid_t starting_vpid;
char* jobid_string;
char* vpid_string;
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:alps setting name"));
id = mca_base_param_register_string("orte", "ess", "jobid", NULL, NULL);
mca_base_param_lookup_string(id, &jobid_string);
if (NULL == jobid_string) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return ORTE_ERR_NOT_FOUND;
}
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_jobid(&jobid, jobid_string))) {
ORTE_ERROR_LOG(rc);
return(rc);
}
id = mca_base_param_register_string("orte", "ess", "vpid", NULL, NULL);
mca_base_param_lookup_string(id, &vpid_string);
if (NULL == vpid_string) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return ORTE_ERR_NOT_FOUND;
}
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_vpid(&starting_vpid, vpid_string))) {
ORTE_ERROR_LOG(rc);
return(rc);
}
ORTE_PROC_MY_NAME->jobid = jobid;
ORTE_PROC_MY_NAME->vpid = (orte_vpid_t) cnos_get_rank() + starting_vpid;
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:alps set name to %s", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
orte_process_info.num_procs = (orte_std_cntr_t) cnos_get_size();
return ORTE_SUCCESS;
}