2005-03-14 20:57:21 +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.
|
2004-11-28 20:09:25 +00:00
|
|
|
* Copyright (c) 2004-2005 High Performance Computing Center Stuttgart,
|
|
|
|
* University of Stuttgart. All rights reserved.
|
2005-03-24 12:43:37 +00:00
|
|
|
* Copyright (c) 2004-2005 The Regents of the University of California.
|
|
|
|
* All rights reserved.
|
2004-11-22 01:38:40 +00:00
|
|
|
* $COPYRIGHT$
|
|
|
|
*
|
|
|
|
* Additional copyrights may follow
|
2004-09-15 18:54:57 +00:00
|
|
|
*
|
|
|
|
* $HEADER$
|
2005-07-27 23:18:16 +00:00
|
|
|
*
|
2004-09-15 18:54:57 +00:00
|
|
|
*/
|
|
|
|
|
2005-03-14 20:57:21 +00:00
|
|
|
#include "orte_config.h"
|
2005-07-27 23:18:16 +00:00
|
|
|
|
2005-04-11 18:43:57 +00:00
|
|
|
#ifdef HAVE_UNISTD_H
|
2005-03-18 03:43:59 +00:00
|
|
|
#include <unistd.h>
|
2005-04-11 04:47:58 +00:00
|
|
|
#endif
|
2005-03-18 03:43:59 +00:00
|
|
|
#include <stdlib.h>
|
2005-05-05 18:25:56 +00:00
|
|
|
#include <errno.h>
|
2005-03-18 03:43:59 +00:00
|
|
|
|
2006-02-12 01:33:29 +00:00
|
|
|
#include "orte/orte_constants.h"
|
|
|
|
#include "orte/util/proc_info.h"
|
2005-07-03 23:31:27 +00:00
|
|
|
#include "opal/util/output.h"
|
2006-02-12 01:33:29 +00:00
|
|
|
#include "opal/mca/base/mca_base_param.h"
|
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
|
|
|
|
|
|
|
#include "orte/dss/dss.h"
|
2006-02-12 01:33:29 +00:00
|
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
#include "orte/mca/ns/ns.h"
|
|
|
|
#include "orte/mca/ns/base/base.h"
|
|
|
|
#include "orte/mca/sds/sds.h"
|
|
|
|
#include "orte/mca/sds/base/base.h"
|
|
|
|
#include "orte/mca/sds/pipe/sds_pipe.h"
|
2005-07-27 23:18:16 +00:00
|
|
|
|
2005-08-02 18:51:28 +00:00
|
|
|
orte_sds_base_module_t orte_sds_pipe_module = {
|
2005-07-27 23:18:16 +00:00
|
|
|
orte_sds_base_basic_contact_universe,
|
|
|
|
orte_sds_pipe_set_name,
|
|
|
|
orte_sds_pipe_finalize,
|
|
|
|
};
|
2004-09-15 18:54:57 +00:00
|
|
|
|
|
|
|
|
2005-07-27 23:18:16 +00:00
|
|
|
int
|
|
|
|
orte_sds_pipe_set_name(void)
|
2005-03-14 20:57:21 +00:00
|
|
|
{
|
2005-07-27 23:18:16 +00:00
|
|
|
int rc, fd, id;
|
2005-03-18 03:43:59 +00:00
|
|
|
orte_process_name_t name;
|
|
|
|
size_t num_procs;
|
|
|
|
|
|
|
|
/* lookup the fd to use */
|
|
|
|
id = mca_base_param_register_int("nds","pipe","fd", NULL, 3);
|
|
|
|
mca_base_param_lookup_int(id, &fd);
|
|
|
|
|
|
|
|
rc = read(fd,&name,sizeof(name));
|
|
|
|
if(rc != sizeof(name)) {
|
|
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
|
|
return ORTE_ERR_NOT_FOUND;
|
|
|
|
}
|
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
|
|
|
if(ORTE_SUCCESS != (rc = orte_dss.copy((void**)&orte_process_info.my_name, &name, ORTE_NAME))) {
|
2005-03-18 03:43:59 +00:00
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
rc = read(fd,&orte_process_info.vpid_start, sizeof(orte_process_info.vpid_start));
|
|
|
|
if(rc != sizeof(orte_process_info.vpid_start)) {
|
2005-07-03 23:31:27 +00:00
|
|
|
opal_output(0, "orte_ns_nds_pipe_get: read returned %d, errno=%d\n", rc, errno);
|
2005-03-18 03:43:59 +00:00
|
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
|
|
return ORTE_ERR_NOT_FOUND;
|
|
|
|
}
|
|
|
|
|
|
|
|
rc = read(fd,&num_procs, sizeof(num_procs));
|
2005-05-05 18:25:56 +00:00
|
|
|
if(rc != sizeof(num_procs)) {
|
2005-07-03 23:31:27 +00:00
|
|
|
opal_output(0, "orte_ns_nds_pipe_get: read returned %d, errno=%d\n", rc, errno);
|
2005-03-18 03:43:59 +00:00
|
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
|
|
return ORTE_ERR_NOT_FOUND;
|
|
|
|
}
|
2006-10-20 02:25:50 +00:00
|
|
|
orte_process_info.num_procs = (orte_std_cntr_t)num_procs;
|
2005-03-18 03:43:59 +00:00
|
|
|
|
|
|
|
close(fd);
|
|
|
|
return ORTE_SUCCESS;
|
2005-03-14 20:57:21 +00:00
|
|
|
}
|
|
|
|
|
2005-03-18 03:43:59 +00:00
|
|
|
|
2005-07-27 23:18:16 +00:00
|
|
|
int
|
|
|
|
orte_sds_pipe_finalize(void)
|
2004-09-15 18:54:57 +00:00
|
|
|
{
|
2005-03-18 03:43:59 +00:00
|
|
|
return ORTE_SUCCESS;
|
2004-09-15 18:54:57 +00:00
|
|
|
}
|