1
1
openmpi/orte/mca/plm/base/base.h
Ralph Castain 5e6928d710 Cleanup recursions in ORTE caused by processing recv'd messages that can cause the system to take action resulting in receipt of another message.
Basically, the method employed here is to have a recv create a zero-time timer event that causes the event library to execute a function that processes the message once the recv returns. Thus, any action taken as a result of processing the message occur outside of a recv.

Created two new macros to assist:

ORTE_MESSAGE_EVENT: creates the zero-time event, passing info in a new orte_message_event_t object

ORTE_PROGRESSED_WAIT: while waiting for specified conditions, just calls progress so messages can be recv'd.

Also fixed the failed_launch function as we no longer block in the orted callback function. Updated the error messages to reflect revision. No change in API to this function, but PLM "owners" may want to check their internal error messages to avoid duplication and excessive output.

This has been tested on Mac, TM, and SLURM.

This commit was SVN r17647.
2008-02-28 19:58:32 +00:00

85 строки
2.0 KiB
C

/*
* Copyright (c) 2004-2006 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2006 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 MCA_PLM_BASE_H
#define MCA_PLM_BASE_H
/*
* includes
*/
#include "orte_config.h"
#include "opal/mca/mca.h"
#include "opal/class/opal_list.h"
#include "orte/mca/plm/plm.h"
BEGIN_C_DECLS
/**
* Struct to hold data for public access
*/
typedef struct orte_plm_base_t {
/** List of opened components */
opal_list_t available_components;
/** indicate a component has been selected */
bool selected;
/** selected component */
orte_plm_base_component_t selected_component;
} orte_plm_base_t;
/**
* Global instance of publicly-accessible PLM framework data
*/
ORTE_DECLSPEC extern orte_plm_base_t orte_plm_base;
/*
* Global functions for MCA overall collective open and close
*/
/**
* Open the plm framework
*/
ORTE_DECLSPEC int orte_plm_base_open(void);
/**
* Select a plm module
*/
ORTE_DECLSPEC int orte_plm_base_select(void);
/**
* Close the plm framework
*/
ORTE_DECLSPEC int orte_plm_base_finalize(void);
ORTE_DECLSPEC int orte_plm_base_close(void);
/**
* Functions that other frameworks may need to call directly
* Specifically, the ODLS needs to access some of these
* to avoid recursive callbacks
*/
ORTE_DECLSPEC void orte_plm_base_app_report_launch(int fd, short event, void *data);
ORTE_DECLSPEC void orte_plm_base_receive_process_msg(int fd, short event, void *data);
END_C_DECLS
#endif