9902748108
Fix two problems that surfaced when using direct launch under SLURM: 1. locally store our own data because some BTLs want to retrieve it during add_procs rather than use what they have internally 2. cleanup MPI_Abort so it correctly passes the error status all the way down to the actual exit. When someone implemented the "abort_peers" API, they left out the error status. So we lost it at that point and *always* exited with a status of 1. This forces a change to the API to include the status. cmr:v1.7.3:reviewer=jsquyres:subject=Fix MPI_Abort and modex_recv for direct launch This commit was SVN r29405.
87 строки
2.7 KiB
C
87 строки
2.7 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) 2004-2010 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) 2010-2011 Oak Ridge National Labs. All rights reserved.
|
|
* Copyright (c) 2011 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @file:
|
|
*/
|
|
|
|
#ifndef ORTE_MCA_ERRMGR_PRIVATE_H
|
|
#define ORTE_MCA_ERRMGR_PRIVATE_H
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
#include "orte/constants.h"
|
|
#include "orte/types.h"
|
|
|
|
#ifdef HAVE_UNISTD_H
|
|
#include <unistd.h>
|
|
#endif /* HAVE_UNISTD_H */
|
|
|
|
#include "opal/dss/dss_types.h"
|
|
#include "orte/mca/plm/plm_types.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
/*
|
|
* Functions for use solely within the ERRMGR framework
|
|
*/
|
|
BEGIN_C_DECLS
|
|
|
|
/* define a struct to hold framework-global values */
|
|
typedef struct {
|
|
opal_list_t error_cbacks;
|
|
} orte_errmgr_base_t;
|
|
|
|
ORTE_DECLSPEC extern orte_errmgr_base_t orte_errmgr_base;
|
|
|
|
/* define a struct to hold registered error callbacks */
|
|
typedef struct {
|
|
opal_list_item_t super;
|
|
orte_errmgr_error_order_t order;
|
|
orte_errmgr_error_callback_fn_t *callback;
|
|
} orte_errmgr_cback_t;
|
|
OBJ_CLASS_DECLARATION(orte_errmgr_cback_t);
|
|
|
|
/* declare the base default module */
|
|
ORTE_DECLSPEC extern orte_errmgr_base_module_t orte_errmgr_default_fns;
|
|
|
|
/*
|
|
* Base functions
|
|
*/
|
|
ORTE_DECLSPEC void orte_errmgr_base_log(int error_code, char *filename, int line);
|
|
|
|
ORTE_DECLSPEC void orte_errmgr_base_abort(int error_code, char *fmt, ...)
|
|
__opal_attribute_format__(__printf__, 2, 3);
|
|
ORTE_DECLSPEC int orte_errmgr_base_abort_peers(orte_process_name_t *procs,
|
|
orte_std_cntr_t num_procs,
|
|
int error_code);
|
|
|
|
ORTE_DECLSPEC void orte_errmgr_base_register_migration_warning(struct timeval *tv);
|
|
|
|
ORTE_DECLSPEC int orte_errmgr_base_register_error_callback(orte_errmgr_error_callback_fn_t *cbfunc,
|
|
orte_errmgr_error_order_t order);
|
|
|
|
ORTE_DECLSPEC void orte_errmgr_base_execute_error_callbacks(opal_pointer_array_t *errors);
|
|
|
|
END_C_DECLS
|
|
#endif
|