1
1
openmpi/orte/mca/iof/base/iof_base_close.c
Ralph Castain 6d6cebb4a7 Bring over the update to terminate orteds that are generated by a dynamic spawn such as comm_spawn. This introduces the concept of a job "family" - i.e., jobs that have a parent/child relationship. Comm_spawn'ed jobs have a parent (the one that spawned them). We track that relationship throughout the lineage - i.e., if a comm_spawned job in turn calls comm_spawn, then it has a parent (the one that spawned it) and a "root" job (the original job that started things).
Accordingly, there are new APIs to the name service to support the ability to get a job's parent, root, immediate children, and all its descendants. In addition, the terminate_job, terminate_orted, and signal_job APIs for the PLS have been modified to accept attributes that define the extent of their actions. For example, doing a "terminate_job" with an attribute of ORTE_NS_INCLUDE_DESCENDANTS will terminate the given jobid AND all jobs that descended from it.

I have tested this capability on a MacBook under rsh, Odin under SLURM, and LANL's Flash (bproc). It worked successfully on non-MPI jobs (both simple and including a spawn), and MPI jobs (again, both simple and with a spawn).

This commit was SVN r12597.
2006-11-14 19:34:59 +00:00

68 строки
1.9 KiB
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
*
* $HEADER$
*/
#include "orte_config.h"
#include <stdio.h>
#include "opal/event/event.h"
#include "opal/mca/mca.h"
#include "opal/mca/base/base.h"
#include "orte/mca/iof/iof.h"
#include "orte/mca/iof/base/base.h"
#include "orte/mca/iof/base/iof_base_endpoint.h"
int orte_iof_base_close(void)
{
opal_list_item_t* item;
/* We only need to flush if an iof component was successfully
selected */
if (orte_iof_base.iof_flush) {
orte_iof_base_flush();
orte_iof_base.iof_flush = false;
}
/* finalize component */
if (NULL != orte_iof.iof_finalize) {
orte_iof.iof_finalize();
}
/* shutdown any remaining opened components */
if (0 != opal_list_get_size(&orte_iof_base.iof_components_opened)) {
mca_base_components_close(orte_iof_base.iof_output,
&orte_iof_base.iof_components_opened, NULL);
}
/* final cleanup of resources */
OPAL_THREAD_LOCK(&orte_iof_base.iof_lock);
while((item = opal_list_remove_first(&orte_iof_base.iof_endpoints)) != NULL) {
OBJ_RELEASE(item);
}
OPAL_THREAD_UNLOCK(&orte_iof_base.iof_lock);
if (NULL != orte_iof_base.iof_service) {
free(orte_iof_base.iof_service);
}
return ORTE_SUCCESS;
}