efbb5c9b7c
* add hnp and orted modules to the errmgr framework. The HNP module contains much of the code that was in the errmgr base since that code could only be executed by the HNP anyway. * update the odls to report process states directly into the active errmgr module, thus removing the need to send messages looped back into the odls cmd processor. Let the active errmgr module decide what to do at various states. * remove the code to track application state progress from the plm_base_launch_support.c code. Update the plm modules to call the errmgr directly when a launch fails. * update the plm_base_receive.c code to call the errmgr with state updates from remote daemons * update the routed modules to reflect that process state is updated in the errmgr * ensure that the orted's open the errmgr and select their appropriate module * add new pretty-print utilities to print process and job state. Move the pretty-print of time info to a globally-accessible place * define a global orte_comm function to send messages from orted's to the HNP so that others can overlay the standard RML methods, if desired. * update the orterun help output to reflect that the "term w/o sync" error message can result from three, not two, scenarios This commit was SVN r23023.
114 строки
3.2 KiB
C
114 строки
3.2 KiB
C
/*
|
|
* 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.
|
|
* 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"
|
|
|
|
#ifdef HAVE_STRING_H
|
|
#include <string.h>
|
|
#endif
|
|
#ifdef HAVE_UNISTD_H
|
|
#include <unistd.h>
|
|
#endif
|
|
#ifdef HAVE_SYS_TYPES_H
|
|
#include <sys/types.h>
|
|
#endif
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/mca/base/base.h"
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
|
|
#include "opal/util/opal_environ.h"
|
|
#include "opal/util/output.h"
|
|
#include "opal/util/trace.h"
|
|
#include "opal/util/output.h"
|
|
|
|
#include "orte/mca/errmgr/base/base.h"
|
|
#include "orte/mca/errmgr/base/errmgr_private.h"
|
|
|
|
#include "orte/mca/errmgr/base/static-components.h"
|
|
|
|
/*
|
|
* Globals
|
|
*/
|
|
int orte_errmgr_base_output = -1;
|
|
bool orte_errmgr_base_enable_recovery = false;
|
|
bool orte_errmgr_base_shutting_down = false;
|
|
bool orte_errmgr_initialized = false;
|
|
opal_list_t orte_errmgr_base_components_available;
|
|
|
|
/* Public module provides a wrapper around previous functions */
|
|
orte_errmgr_API_t orte_errmgr = {
|
|
orte_errmgr_base_log,
|
|
orte_errmgr_base_update_state,
|
|
orte_errmgr_base_predicted_fault,
|
|
orte_errmgr_base_suggest_map_targets,
|
|
orte_errmgr_base_abort
|
|
};
|
|
|
|
/**
|
|
* Function for finding and opening either all MCA components, or the one
|
|
* that was specifically requested via a MCA parameter.
|
|
*/
|
|
int orte_errmgr_base_open(void)
|
|
{
|
|
int value;
|
|
|
|
OPAL_TRACE(5);
|
|
|
|
/* Only pass this way once */
|
|
if( orte_errmgr_initialized ) {
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
OBJ_CONSTRUCT(&orte_errmgr_base_modules, opal_pointer_array_t);
|
|
|
|
orte_errmgr_base_output = opal_output_open(NULL);
|
|
|
|
mca_base_param_reg_int_name("errmgr",
|
|
"base_enable_recovery",
|
|
"If the ErrMgr recovery components should be enabled."
|
|
" [Default = disabled]",
|
|
false, false,
|
|
0, &value);
|
|
orte_errmgr_base_enable_recovery = OPAL_INT_TO_BOOL(value);
|
|
|
|
/*
|
|
* A flag to indicate that orterun is shutting down, so skip the recovery
|
|
* logic.
|
|
*/
|
|
orte_errmgr_base_shutting_down = false;
|
|
|
|
/*
|
|
* Open up all available components
|
|
*/
|
|
if (ORTE_SUCCESS !=
|
|
mca_base_components_open("errmgr",
|
|
orte_errmgr_base_output,
|
|
mca_errmgr_base_static_components,
|
|
&orte_errmgr_base_components_available,
|
|
true)) {
|
|
return ORTE_ERROR;
|
|
}
|
|
|
|
orte_errmgr_initialized = true;
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|