1
1
openmpi/orte/mca/ess/alps/ess_alps_module.c
Ralph Castain b44f8d4b28 Complete implementation of the ess.proc_get_locality API. Up to this point, the API was only capable of telling if the specified proc was sharing a node with you. However, the returned value was capable of telling you much more detailed info - e.g., if the proc shares a socket, a cache, or numa node. We just didn't have the data to provide that detail.
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.
2011-10-19 20:18:14 +00:00

240 строки
7.2 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.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*
*/
#include "orte_config.h"
#include "orte/constants.h"
#if defined(HAVE_CNOS_MPI_OS_H)
# include "cnos_mpi_os.h"
#elif defined(HAVE_CATAMOUNT_CNOS_MPI_OS_H)
# include "catamount/cnos_mpi_os.h"
#endif
#include "orte/util/show_help.h"
#include "opal/mca/paffinity/paffinity.h"
#include "opal/util/argv.h"
#include "orte/util/proc_info.h"
#include "orte/mca/errmgr/base/base.h"
#include "orte/util/name_fns.h"
#include "orte/util/nidmap.h"
#include "orte/util/regex.h"
#include "orte/runtime/orte_globals.h"
#include "orte/mca/ess/ess.h"
#include "orte/mca/ess/base/base.h"
#include "orte/mca/ess/alps/ess_alps.h"
static int alps_set_name(void);
static int rte_init(void);
static int rte_finalize(void);
orte_ess_base_module_t orte_ess_alps_module = {
rte_init,
rte_finalize,
orte_ess_base_app_abort,
orte_ess_base_proc_get_locality,
orte_ess_base_proc_get_daemon,
orte_ess_base_proc_get_hostname,
orte_ess_base_proc_get_local_rank,
orte_ess_base_proc_get_node_rank,
orte_ess_base_proc_get_epoch,
orte_ess_base_update_pidmap,
orte_ess_base_update_nidmap,
NULL /* ft_event */
};
/*
* Local variables
*/
static orte_node_rank_t my_node_rank=ORTE_NODE_RANK_INVALID;
static orte_vpid_t starting_vpid=0;
static int rte_init(void)
{
int ret, i;
char *error = NULL;
char **hosts = NULL;
/* run the prolog */
if (ORTE_SUCCESS != (ret = orte_ess_base_std_prolog())) {
error = "orte_ess_base_std_prolog";
goto error;
}
/* Start by getting a unique name */
alps_set_name();
/* if I am a daemon, complete my setup using the
* default procedure
*/
if (ORTE_PROC_IS_DAEMON) {
if (NULL != orte_node_regex) {
/* extract the nodes */
if (ORTE_SUCCESS != (ret = orte_regex_extract_node_names(orte_node_regex, &hosts)) ||
NULL == hosts) {
error = "orte_regex_extract_node_names";
goto error;
}
}
/* find our host in the list */
for (i=0; NULL != hosts[i]; i++) {
if (0 == strncmp(hosts[i], orte_process_info.nodename, strlen(hosts[i]))) {
/* correct our vpid */
ORTE_PROC_MY_NAME->vpid = starting_vpid + i;
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:alps reset name to %s",
ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
break;
}
}
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_setup(hosts))) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_orted_setup";
goto error;
}
opal_argv_free(hosts);
return ORTE_SUCCESS;
}
if (ORTE_PROC_IS_TOOL) {
/* otherwise, if I am a tool proc, use that procedure */
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_setup())) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_tool_setup";
goto error;
}
/* as a tool, I don't need a nidmap - so just return now */
return ORTE_SUCCESS;
}
/* otherwise, I must be an application process - use
* the default procedure to finish my setup
*/
if (ORTE_SUCCESS != (ret = orte_ess_base_app_setup())) {
ORTE_ERROR_LOG(ret);
error = "orte_ess_base_app_setup";
goto error;
}
/* setup the nidmap arrays */
if (ORTE_SUCCESS != (ret = orte_util_nidmap_init(orte_process_info.sync_buf))) {
ORTE_ERROR_LOG(ret);
error = "orte_util_nidmap_init";
goto error;
}
return ORTE_SUCCESS;
error:
orte_show_help("help-orte-runtime.txt",
"orte_init:startup:internal-failure",
true, error, ORTE_ERROR_NAME(ret), ret);
return ret;
}
static int rte_finalize(void)
{
int ret;
/* if I am a daemon, finalize using the default procedure */
if (ORTE_PROC_IS_DAEMON) {
if (ORTE_SUCCESS != (ret = orte_ess_base_orted_finalize())) {
ORTE_ERROR_LOG(ret);
}
} else if (ORTE_PROC_IS_TOOL) {
/* otherwise, if I am a tool proc, use that procedure */
if (ORTE_SUCCESS != (ret = orte_ess_base_tool_finalize())) {
ORTE_ERROR_LOG(ret);
}
/* as a tool, I didn't create a nidmap - so just return now */
return ret;
} else {
/* otherwise, I must be an application process
* use the default procedure to finish
*/
if (ORTE_SUCCESS != (ret = orte_ess_base_app_finalize())) {
ORTE_ERROR_LOG(ret);
}
}
/* deconstruct my nidmap and jobmap arrays */
orte_util_nidmap_finalize();
return ret;
}
static int alps_set_name(void)
{
int rc;
orte_jobid_t jobid;
char* tmp;
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:alps setting name"));
mca_base_param_reg_string_name("orte", "ess_jobid", "Process jobid",
true, false, NULL, &tmp);
if (NULL == tmp) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return ORTE_ERR_NOT_FOUND;
}
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_jobid(&jobid, tmp))) {
ORTE_ERROR_LOG(rc);
return(rc);
}
free(tmp);
mca_base_param_reg_string_name("orte", "ess_vpid", "Process vpid",
true, false, NULL, &tmp);
if (NULL == tmp) {
ORTE_ERROR_LOG(ORTE_ERR_NOT_FOUND);
return ORTE_ERR_NOT_FOUND;
}
if (ORTE_SUCCESS != (rc = orte_util_convert_string_to_vpid(&starting_vpid, tmp))) {
ORTE_ERROR_LOG(rc);
return(rc);
}
free(tmp);
ORTE_PROC_MY_NAME->jobid = jobid;
ORTE_PROC_MY_NAME->vpid = (orte_vpid_t) cnos_get_rank() + starting_vpid;
ORTE_EPOCH_SET(ORTE_PROC_MY_NAME->epoch,ORTE_EPOCH_INVALID);
ORTE_EPOCH_SET(ORTE_PROC_MY_NAME->epoch,orte_ess.proc_get_epoch(ORTE_PROC_MY_NAME));
OPAL_OUTPUT_VERBOSE((1, orte_ess_base_output,
"ess:alps set name to %s", ORTE_NAME_PRINT(ORTE_PROC_MY_NAME)));
/* get the num procs as provided in the cmd line param */
if (ORTE_SUCCESS != (rc = orte_ess_env_get())) {
ORTE_ERROR_LOG(rc);
return rc;
}
if (orte_process_info.max_procs < orte_process_info.num_procs) {
orte_process_info.max_procs = orte_process_info.num_procs;
}
return ORTE_SUCCESS;
}