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.
72 строки
2.1 KiB
C
72 строки
2.1 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_BASE_H
|
|
#define ORTE_MCA_ERRMGR_BASE_H
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
#include "orte/constants.h"
|
|
|
|
#include "opal/class/opal_list.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/*
|
|
* MCA Framework functions
|
|
*/
|
|
ORTE_DECLSPEC int orte_errmgr_base_open(void);
|
|
ORTE_DECLSPEC int orte_errmgr_base_select(void);
|
|
ORTE_DECLSPEC int orte_errmgr_base_close(void);
|
|
|
|
/**
|
|
* Composite Stack states
|
|
*/
|
|
#define ORTE_ERRMGR_STACK_STATE_NONE 0x00 /* No actions have been performed */
|
|
#define ORTE_ERRMGR_STACK_STATE_UPDATED 0x01 /* Updated the runtime */
|
|
#define ORTE_ERRMGR_STACK_STATE_CONTINUE 0x02 /* Continue running without this process */
|
|
#define ORTE_ERRMGR_STACK_STATE_RECOVERED 0x04 /* Process has been recovered */
|
|
#define ORTE_ERRMGR_STACK_STATE_JOB_ABORT 0x08 /* Abort this job, cannot recover */
|
|
#define ORTE_ERRMGR_STACK_STATE_COMPLETE 0x10 /* done processing this command */
|
|
/**
|
|
* Output and component variables
|
|
*/
|
|
ORTE_DECLSPEC extern opal_list_t orte_errmgr_base_components_available;
|
|
ORTE_DECLSPEC extern int orte_errmgr_base_output;
|
|
ORTE_DECLSPEC extern bool orte_errmgr_base_shutting_down;
|
|
ORTE_DECLSPEC extern bool orte_errmgr_base_enable_recovery;
|
|
|
|
extern opal_pointer_array_t orte_errmgr_base_modules;
|
|
extern bool orte_errmgr_initialized;
|
|
|
|
/*
|
|
* Additional External API function declared in errmgr.h
|
|
*/
|
|
|
|
END_C_DECLS
|
|
|
|
#endif
|