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.
53 строки
883 B
C
53 строки
883 B
C
/*
|
|
* Copyright (c) 2009 Cisco Systems, Inc. All rights reserved.
|
|
*
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @file:
|
|
*/
|
|
|
|
#ifndef MCA_SENSOR_BASE_H
|
|
#define MCA_SENSOR_BASE_H
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
|
|
#include "opal/class/opal_list.h"
|
|
#include "opal/mca/mca.h"
|
|
|
|
#include "orte/mca/sensor/sensor.h"
|
|
|
|
|
|
/*
|
|
* Global functions for MCA overall collective open and close
|
|
*/
|
|
BEGIN_C_DECLS
|
|
|
|
/*
|
|
* function definitions
|
|
*/
|
|
ORTE_DECLSPEC int orte_sensor_base_open(void);
|
|
ORTE_DECLSPEC int orte_sensor_base_select(void);
|
|
ORTE_DECLSPEC int orte_sensor_base_close(void);
|
|
|
|
/*
|
|
* globals that might be needed
|
|
*/
|
|
|
|
ORTE_DECLSPEC extern opal_list_t mca_sensor_base_components_available;
|
|
|
|
#if !ORTE_DISABLE_FULL_SUPPORT
|
|
|
|
/* no base functions to protect at this time */
|
|
|
|
#endif /* ORTE_DISABLE_FULL_SUPPORT */
|
|
|
|
END_C_DECLS
|
|
#endif
|