b9893aacc5
1. file activity - can monitor file size, access and modification times. If these fail to change over a specified number of sampling iterations (rate is an mca param), then the errmgr is notified. 2. memory usage - checks amount of memory used by a process. Limit and sampling rate can be set. This support must be enabled by configuring --enable-sensors. ompi_info and orte-info have been updated to include the new framework. Also includes some initial steps toward restoring the recovery capability. Most notably, the ODLS API has been extended to include a "restart_proc" entry for restarting a local process, and organizes the various ERRMGR framework globals into a single struct as we do in the other ORTE frameworks. Fix an oversight in the ERRMGR framework where a pointer array was constructed, but not initialized. Implementation continues. This commit was SVN r23043.
92 строки
2.9 KiB
C
92 строки
2.9 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
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @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"
|
|
|
|
#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 {
|
|
int output;
|
|
bool shutting_down;
|
|
bool enable_recovery;
|
|
opal_pointer_array_t modules;
|
|
bool initialized;
|
|
int max_global_restarts;
|
|
int max_local_restarts;
|
|
} orte_errmgr_base_t;
|
|
|
|
ORTE_DECLSPEC extern orte_errmgr_base_t orte_errmgr_base;
|
|
|
|
/* Define the ERRMGR command flag */
|
|
typedef uint8_t orte_errmgr_cmd_flag_t;
|
|
#define ORTE_ERRMGR_CMD OPAL_UINT8
|
|
|
|
/* define some commands */
|
|
#define ORTE_ERRMGR_ABORT_PROCS_REQUEST_CMD 0x01
|
|
#define ORTE_ERRMGR_REGISTER_CALLBACK_CMD 0x02
|
|
|
|
/*
|
|
* Base functions
|
|
*/
|
|
ORTE_DECLSPEC void orte_errmgr_base_log(int error_code, char *filename, int line);
|
|
|
|
ORTE_DECLSPEC int orte_errmgr_base_update_state(orte_jobid_t job,
|
|
orte_job_state_t jobstate,
|
|
orte_process_name_t *proc_name,
|
|
orte_proc_state_t state,
|
|
orte_exit_code_t exit_code);
|
|
ORTE_DECLSPEC int orte_errmgr_base_abort(int error_code, char *fmt, ...)
|
|
# if OPAL_HAVE_ATTRIBUTE_FORMAT_FUNCPTR
|
|
__opal_attribute_format__(__printf__, 2, 3)
|
|
# endif
|
|
;
|
|
ORTE_DECLSPEC int orte_errmgr_base_predicted_fault(char ***proc_list,
|
|
char ***node_list,
|
|
char ***suggested_nodes);
|
|
ORTE_DECLSPEC int orte_errmgr_base_suggest_map_targets(orte_proc_t *proc,
|
|
orte_node_t *oldnode,
|
|
opal_list_t *node_list);
|
|
ORTE_DECLSPEC int orte_errmgr_base_ft_event(int state);
|
|
|
|
/*
|
|
* Additional External API function declared in errmgr.h
|
|
*/
|
|
|
|
END_C_DECLS
|
|
#endif
|