b44f8d4b28
Use hwloc to obtain the cpuset for each process during mpi_init, and share that info in the modex. As it arrives, use a new opal_hwloc_base utility function to parse the value against the local proc's cpuset and determine where they overlap. Cache the value in the pmap object as it may be referenced multiple times. Thus, the return value from orte_ess.proc_get_locality is a 16-bit bitmask that describes the resources being shared with you. This bitmask can be tested using the macros in opal/mca/paffinity/paffinity.h Locality is available for all procs, whether launched via mpirun or directly with an external launcher such as slurm or aprun. This commit was SVN r25331.
165 строки
4.7 KiB
C
165 строки
4.7 KiB
C
/*
|
|
* Copyright (c) 2004-2005 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2011 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 (c) 2011 Cisco Systems, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "orte_config.h"
|
|
#include "orte/constants.h"
|
|
|
|
#ifdef HAVE_UNISTD_H
|
|
#include <unistd.h>
|
|
#endif
|
|
#include <stdlib.h>
|
|
#include <errno.h>
|
|
|
|
#include "opal/util/output.h"
|
|
#include "opal/mca/paffinity/paffinity.h"
|
|
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
#include "orte/util/name_fns.h"
|
|
#include "orte/util/nidmap.h"
|
|
#include "orte/util/proc_info.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
#include "orte/mca/ess/base/base.h"
|
|
|
|
opal_paffinity_locality_t orte_ess_base_proc_get_locality(orte_process_name_t *proc)
|
|
{
|
|
orte_pmap_t *pmap;
|
|
|
|
if (NULL == (pmap = orte_util_lookup_pmap(proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return OPAL_PROC_NON_LOCAL;
|
|
}
|
|
|
|
return pmap->locality;
|
|
}
|
|
|
|
orte_vpid_t orte_ess_base_proc_get_daemon(orte_process_name_t *proc)
|
|
{
|
|
orte_nid_t *nid;
|
|
|
|
if( ORTE_JOBID_IS_DAEMON(proc->jobid) ) {
|
|
return proc->vpid;
|
|
}
|
|
|
|
if (NULL == (nid = orte_util_lookup_nid(proc))) {
|
|
return ORTE_VPID_INVALID;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((5, orte_ess_base_output,
|
|
"%s ess:base: proc %s is hosted by daemon %s",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
ORTE_VPID_PRINT(nid->daemon)));
|
|
|
|
return nid->daemon;
|
|
}
|
|
|
|
char* orte_ess_base_proc_get_hostname(orte_process_name_t *proc)
|
|
{
|
|
orte_nid_t *nid;
|
|
|
|
if (NULL == (nid = orte_util_lookup_nid(proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return NULL;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((5, orte_ess_base_output,
|
|
"%s ess:base: proc %s is on host %s",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
nid->name));
|
|
|
|
return nid->name;
|
|
}
|
|
|
|
orte_local_rank_t orte_ess_base_proc_get_local_rank(orte_process_name_t *proc)
|
|
{
|
|
orte_pmap_t *pmap;
|
|
|
|
if (NULL == (pmap = orte_util_lookup_pmap(proc))) {
|
|
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
|
|
return ORTE_LOCAL_RANK_INVALID;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((5, orte_ess_base_output,
|
|
"%s ess:base: proc %s has local rank %d",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
(int)pmap->local_rank));
|
|
|
|
return pmap->local_rank;
|
|
}
|
|
|
|
orte_node_rank_t orte_ess_base_proc_get_node_rank(orte_process_name_t *proc)
|
|
{
|
|
orte_pmap_t *pmap;
|
|
orte_ns_cmp_bitmask_t mask;
|
|
|
|
mask = ORTE_NS_CMP_JOBID | ORTE_NS_CMP_VPID;
|
|
|
|
/* is this me? */
|
|
if (OPAL_EQUAL == orte_util_compare_name_fields(mask, proc, ORTE_PROC_MY_NAME)) {
|
|
/* yes it is - reply with my rank. This is necessary
|
|
* because the pidmap will not have arrived when I
|
|
* am starting up, and if we use static ports, then
|
|
* I need to know my node rank during init
|
|
*/
|
|
return orte_process_info.my_node_rank;
|
|
}
|
|
|
|
if (NULL == (pmap = orte_util_lookup_pmap(proc))) {
|
|
return ORTE_NODE_RANK_INVALID;
|
|
}
|
|
|
|
OPAL_OUTPUT_VERBOSE((5, orte_ess_base_output,
|
|
"%s ess:base: proc %s has node rank %d",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME),
|
|
ORTE_NAME_PRINT(proc),
|
|
(int)pmap->node_rank));
|
|
|
|
return pmap->node_rank;
|
|
}
|
|
|
|
int orte_ess_base_update_pidmap(opal_byte_object_t *bo)
|
|
{
|
|
int ret;
|
|
|
|
OPAL_OUTPUT_VERBOSE((2, orte_ess_base_output,
|
|
"%s ess:base: updating pidmap",
|
|
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
|
|
|
|
/* build the pmap */
|
|
if (ORTE_SUCCESS != (ret = orte_util_decode_pidmap(bo))) {
|
|
ORTE_ERROR_LOG(ret);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
int orte_ess_base_update_nidmap(opal_byte_object_t *bo)
|
|
{
|
|
int rc;
|
|
/* decode the nidmap - the util will know what to do */
|
|
if (ORTE_SUCCESS != (rc = orte_util_decode_nodemap(bo))) {
|
|
ORTE_ERROR_LOG(rc);
|
|
}
|
|
return rc;
|
|
}
|
|
|