2005-07-27 23:18:16 +00:00
|
|
|
/*
|
2005-11-05 19:57:48 +00:00
|
|
|
* 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.
|
2005-07-27 23:18:16 +00:00
|
|
|
* 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"
|
|
|
|
|
2006-02-12 01:33:29 +00:00
|
|
|
#include "orte/orte_constants.h"
|
|
|
|
#include "orte/mca/sds/sds.h"
|
|
|
|
#include "orte/mca/sds/base/base.h"
|
|
|
|
#include "orte/mca/sds/singleton/sds_singleton.h"
|
|
|
|
#include "orte/util/proc_info.h"
|
|
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
#include "orte/mca/ns/base/base.h"
|
2005-07-27 23:18:16 +00:00
|
|
|
#include "opal/util/output.h"
|
|
|
|
|
|
|
|
|
2005-08-02 18:51:28 +00:00
|
|
|
orte_sds_base_module_t orte_sds_singleton_module = {
|
2005-07-27 23:18:16 +00:00
|
|
|
orte_sds_base_basic_contact_universe,
|
|
|
|
orte_sds_singleton_set_name,
|
|
|
|
orte_sds_singleton_finalize,
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
int
|
|
|
|
orte_sds_singleton_set_name(void)
|
|
|
|
{
|
|
|
|
int rc, id, flag;
|
|
|
|
orte_vpid_t vpid;
|
|
|
|
|
|
|
|
if (ORTE_SUCCESS != (rc = orte_ns.create_my_name())) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
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
|
|
|
vpid = ORTE_PROC_MY_NAME->vpid;
|
2005-07-27 23:18:16 +00:00
|
|
|
|
|
|
|
orte_process_info.num_procs = 1;
|
|
|
|
orte_process_info.vpid_start = vpid;
|
2005-08-25 19:13:22 +00:00
|
|
|
/* only set the singleton flag is we are NOT infrastructure,
|
|
|
|
and it has not been previously set. */
|
2005-08-26 20:13:35 +00:00
|
|
|
id = mca_base_param_find("orte", NULL, "infrastructure");
|
2005-07-27 23:18:16 +00:00
|
|
|
mca_base_param_lookup_int(id, &flag);
|
|
|
|
if (!flag) {
|
|
|
|
orte_process_info.singleton = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ORTE_SUCCESS;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
int
|
|
|
|
orte_sds_singleton_finalize(void)
|
|
|
|
{
|
2006-02-12 01:33:29 +00:00
|
|
|
return ORTE_SUCCESS;
|
2005-07-27 23:18:16 +00:00
|
|
|
}
|