1
1
openmpi/orte/mca/odls/default/odls_default_component.c
Ralph Castain 1dc12046f1 Modify the OMPI paffinity and mapping system to support socket-level mapping and binding. Mostly refactors existing code, with modifications to the odls_default module to support the new capabilities.
Adds several new mpirun options:

* -bysocket - assign ranks on a node by socket. Effectively load balances the procs assigned to a node across the available sockets. Note that ranks can still be bound to a specific core within the socket, or to the entire socket - the mapping is independent of the binding.

* -bind-to-socket - bind each rank to all the cores on the socket to which they are assigned.

* -bind-to-core - currently the default behavior (maintained from prior default)

* -npersocket N - launch N procs for every socket on a node. Note that this implies we know how many sockets are on a node. Mpirun will determine its local values. These can be overridden by provided values, either via MCA param or in a hostfile

Similar features/options are provided at the board level for multi-board nodes.

Documentation to follow...

This commit was SVN r21791.
2009-08-11 02:51:27 +00:00

97 строки
2.9 KiB
C

/*
* Copyright (c) 2004-2008 The Trustees of Indiana University and Indiana
* University Research and Technology
* Corporation. All rights reserved.
* Copyright (c) 2004-2006 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
*
* $HEADER$
*
* These symbols are in a file by themselves to provide nice linker
* semantics. Since linkers generally pull in symbols by object
* files, keeping these symbols as the only symbols in this file
* prevents utility programs such as "ompi_info" from having to import
* entire components just to query their version and parameters.
*/
#include "orte_config.h"
#include "orte/constants.h"
#include <stdlib.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#include <ctype.h>
#include "orte/mca/odls/odls.h"
#include "orte/mca/odls/base/odls_private.h"
#include "orte/mca/odls/default/odls_default.h"
/* instantiate a module-global variable */
bool orte_odls_default_report_bindings;
/*
* Instantiate the public struct with all of our public information
* and pointers to our public functions in it
*/
orte_odls_base_component_t mca_odls_default_component = {
/* First, the mca_component_t struct containing meta information
about the component itself */
{
ORTE_ODLS_BASE_VERSION_2_0_0,
/* Component name and version */
"default",
ORTE_MAJOR_VERSION,
ORTE_MINOR_VERSION,
ORTE_RELEASE_VERSION,
/* Component open and close functions */
orte_odls_default_component_open,
orte_odls_default_component_close,
orte_odls_default_component_query
},
{
/* The component is checkpoint ready */
MCA_BASE_METADATA_PARAM_CHECKPOINT
}
};
int orte_odls_default_component_open(void)
{
return ORTE_SUCCESS;
}
int orte_odls_default_component_query(mca_base_module_t **module, int *priority)
{
/* the base open/select logic protects us against operation when
* we are NOT in a daemon, so we don't have to check that here
*/
/* we have built some logic into the configure.m4 file that checks
* to see if we have "fork" support and only builds this component
* if we do. Hence, we only get here if we CAN build - in which
* case, we definitely should be considered for selection
*/
*priority = 1; /* let others override us - we are the default */
*module = (mca_base_module_t *) &orte_odls_default_module;
return ORTE_SUCCESS;
}
int orte_odls_default_component_close(void)
{
return ORTE_SUCCESS;
}