2006-09-14 21:29:51 +00:00
|
|
|
/* -*- 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/orte_types.h"
|
|
|
|
|
|
|
|
#include "opal/util/output.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
|
|
|
|
|
|
#include "orte/dss/dss.h"
|
|
|
|
#include "orte/util/proc_info.h"
|
|
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
#include "orte/mca/rml/rml.h"
|
|
|
|
|
|
|
|
#include "orte/mca/rds/base/rds_private.h"
|
|
|
|
|
|
|
|
static bool recv_issued=false;
|
|
|
|
|
|
|
|
int orte_rds_base_comm_start(void)
|
|
|
|
{
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
if (recv_issued) {
|
|
|
|
return ORTE_SUCCESS;
|
|
|
|
}
|
|
|
|
|
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_rml.recv_buffer_nb(ORTE_NAME_WILDCARD,
|
2006-09-14 21:29:51 +00:00
|
|
|
ORTE_RML_TAG_RDS,
|
|
|
|
ORTE_RML_PERSISTENT,
|
|
|
|
orte_rds_base_recv,
|
|
|
|
NULL))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
}
|
|
|
|
recv_issued = true;
|
|
|
|
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2006-10-02 00:46:31 +00:00
|
|
|
int orte_rds_base_comm_stop(void)
|
|
|
|
{
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
if (!recv_issued) {
|
|
|
|
return ORTE_SUCCESS;
|
|
|
|
}
|
|
|
|
|
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_rml.recv_cancel(ORTE_NAME_WILDCARD, ORTE_RML_TAG_RDS))) {
|
2006-10-02 00:46:31 +00:00
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
}
|
|
|
|
recv_issued = false;
|
|
|
|
|
|
|
|
return rc;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2006-09-14 21:29:51 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* handle message from proxies
|
|
|
|
* NOTE: The incoming buffer "buffer" is OBJ_RELEASED by the calling program.
|
|
|
|
* DO NOT RELEASE THIS BUFFER IN THIS CODE
|
|
|
|
*/
|
|
|
|
|
|
|
|
void orte_rds_base_recv(int status, orte_process_name_t* sender,
|
|
|
|
orte_buffer_t* buffer, orte_rml_tag_t tag,
|
|
|
|
void* cbdata)
|
|
|
|
{
|
|
|
|
orte_buffer_t answer;
|
|
|
|
orte_rds_cmd_flag_t command;
|
2006-12-06 15:59:34 +00:00
|
|
|
orte_jobid_t job;
|
2006-09-14 21:29:51 +00:00
|
|
|
orte_std_cntr_t count;
|
|
|
|
int rc;
|
|
|
|
|
|
|
|
count = 1;
|
|
|
|
if (ORTE_SUCCESS != (rc = orte_dss.unpack(buffer, &command, &count, ORTE_RDS_CMD))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
OBJ_CONSTRUCT(&answer, orte_buffer_t);
|
|
|
|
|
|
|
|
switch (command) {
|
|
|
|
case ORTE_RDS_QUERY_CMD:
|
2006-12-06 15:59:34 +00:00
|
|
|
count = 1;
|
|
|
|
if (ORTE_SUCCESS != (rc = orte_dss.unpack(buffer, &job, &count, ORTE_JOBID))) {
|
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ORTE_SUCCESS != (rc = orte_dss.pack(&answer, &command, 1, ORTE_RDS_CMD))) {
|
2006-09-14 21:29:51 +00:00
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
}
|
|
|
|
|
2006-12-06 15:59:34 +00:00
|
|
|
if (ORTE_SUCCESS != (rc = orte_rds_base_query(job))) {
|
2006-09-14 21:29:51 +00:00
|
|
|
ORTE_ERROR_LOG(rc);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (0 > orte_rml.send_buffer(sender, &answer, tag, 0)) {
|
|
|
|
ORTE_ERROR_LOG(ORTE_ERR_COMM_FAILURE);
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
ORTE_ERROR_LOG(ORTE_ERR_VALUE_OUT_OF_BOUNDS);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* cleanup */
|
|
|
|
OBJ_DESTRUCT(&answer);
|
|
|
|
}
|
|
|
|
|