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.
66 строки
1.9 KiB
C
66 строки
1.9 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_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;
|
|
|
|
/*
|
|
* Additional External API function declared in errmgr.h
|
|
*/
|
|
|
|
END_C_DECLS
|
|
|
|
#endif
|