ab5ea61100
1. add a "cancel_operation" API to the pls components that allows orterun to demand that an orted operation (e.g., terminate_job) be immediately cancelled and abandoned. 2. changes the pls orted commands from blocking to non-blocking. This allows us to interrupt those operations should an orted be non-responsive. The change also adds an orte_abort_timeout that limits how long orterun will automatically wait for the orteds to respond - if the terminate command, for example, doesn't see orted response within that time, then we printout an appropriate error message and just give up. 3. modifies orterun to allow multiple ctrl-c's to simply abort the program even if the orteds have not responded 4. does some cleanup on the orte-level mca params so that their implementation looks a lot more like that of ompi - makes it easier to maintain. This change also includes the definition of an orte_abort_timeout struct and associated MCA param (can't have too many!) so you can set the time after which orterun gives up on waiting for orteds to respond This needs more testing before migrating to 1.2. This commit was SVN r13304.
125 строки
2.8 KiB
C
125 строки
2.8 KiB
C
/* -*- C -*-
|
|
*
|
|
* Copyright (c) 2004-2005 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:
|
|
*
|
|
*/
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
|
|
#include "orte/orte_constants.h"
|
|
#include "orte/util/proc_info.h"
|
|
#include "opal/util/output.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
|
|
#include "orte/mca/pls/base/pls_private.h"
|
|
#include "pls_proxy.h"
|
|
|
|
/*
|
|
* Struct of function pointers that need to be initialized
|
|
*/
|
|
orte_pls_base_component_t mca_pls_proxy_component = {
|
|
{
|
|
ORTE_PLS_BASE_VERSION_1_3_0,
|
|
|
|
"proxy", /* MCA module name */
|
|
ORTE_MAJOR_VERSION, /* MCA module major version */
|
|
ORTE_MINOR_VERSION, /* MCA module minor version */
|
|
ORTE_RELEASE_VERSION, /* MCA module release version */
|
|
orte_pls_proxy_open, /* module open */
|
|
orte_pls_proxy_close /* module close */
|
|
},
|
|
{
|
|
false /* checkpoint / restart */
|
|
},
|
|
orte_pls_proxy_init /* module init */
|
|
};
|
|
|
|
/*
|
|
* setup the function pointers for the module
|
|
*/
|
|
static orte_pls_base_module_t orte_pls_proxy_module = {
|
|
orte_pls_proxy_launch,
|
|
orte_pls_proxy_terminate_job,
|
|
orte_pls_proxy_terminate_orteds,
|
|
orte_pls_proxy_terminate_proc,
|
|
orte_pls_proxy_signal_job,
|
|
orte_pls_proxy_signal_proc,
|
|
orte_pls_proxy_cancel_operation,
|
|
orte_pls_proxy_finalize
|
|
};
|
|
|
|
/*
|
|
* Whether or not we allowed this component to be selected
|
|
*/
|
|
static bool initialized = false;
|
|
|
|
/* the name of our replica */
|
|
orte_process_name_t *orte_pls_proxy_replica;
|
|
|
|
/*
|
|
* Not much to do here.
|
|
*/
|
|
int orte_pls_proxy_open(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
/*
|
|
* ditto for this one
|
|
*/
|
|
int orte_pls_proxy_close(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
orte_pls_base_module_t* orte_pls_proxy_init(int *priority)
|
|
{
|
|
/* If we are an HNP, then don't pick us */
|
|
if (orte_process_info.seed) {
|
|
return NULL;
|
|
}
|
|
|
|
/* define the replica for us to use - for now, just point
|
|
* to the name service replica
|
|
*/
|
|
orte_pls_proxy_replica = orte_process_info.ns_replica;
|
|
|
|
initialized = true;
|
|
*priority = 1;
|
|
return &orte_pls_proxy_module;
|
|
}
|
|
|
|
|
|
/*
|
|
* finalize routine
|
|
*/
|
|
int orte_pls_proxy_finalize(void)
|
|
{
|
|
initialized = false;
|
|
|
|
/* All done */
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|