a89dc623b0
anything for non-MPI apps. Oops! (But before you freak out, gentle reader, note that mpi_paffinity_alone for MPI apps still worked fine) When we made the switchover somewhere in the 1.3 series to have the orted's do processor binding, then stuff like: mpirun --mca mpi_paffinity_alone 1 hostname should have bound hostname to processor 0. But it didn't because of a subtle startup ordering issue: the MCA param registration for opal_paffinity_alone was in the paffinity base (vs. being in opal/runtime/opal_params.c), but it didn't actually get registered until after the global variable opal_paffinity_alone was checked to see if we wanted old-style affinity bindings. Oops. However, for MPI apps, even though the orted didn't do the binding, ompi_mpi_init() would notice that opal_paffinity_alone was set, yet the process didn't seem to be bound. So the MPI process would bind itself (this was done to support the running-without-orteds scenarios). Hence, MPI apps still obeyed mpi_paffinity_alone semantics. But note that the error described above caused the new mpirun switch --report-bindings to not work with mpi_paffinity_alone=1, meaning that the orted would not report the bindings when mpi_paffinity_alone was set to 1 (it ''did'' correctly report bindings if you used --bind-to-core or one of the other binding options). This commit separates out the paffinity base MCA param registration into a small function that can be called at the Right place during the startup sequence. This commit was SVN r22602.
112 строки
3.8 KiB
C
112 строки
3.8 KiB
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 (c) 2008-2010 Cisco Systems, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
|
|
#include "opal_config.h"
|
|
|
|
#include "opal/constants.h"
|
|
#include "opal/util/output.h"
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/mca/base/base.h"
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
#include "opal/mca/paffinity/paffinity.h"
|
|
#include "opal/mca/paffinity/base/base.h"
|
|
|
|
|
|
/*
|
|
* The following file was created by configure. It contains extern
|
|
* statements and the definition of an array of pointers to each
|
|
* component's public mca_base_component_t struct.
|
|
*/
|
|
#include "opal/mca/paffinity/base/static-components.h"
|
|
|
|
|
|
/*
|
|
* Globals
|
|
*/
|
|
OPAL_DECLSPEC int opal_paffinity_base_output = -1;
|
|
bool opal_paffinity_base_components_opened_valid = false;
|
|
opal_list_t opal_paffinity_base_components_opened;
|
|
bool opal_paffinity_alone = false;
|
|
char *opal_paffinity_base_slot_list;
|
|
|
|
/*
|
|
* Register some paffinity-wide MCA params
|
|
*/
|
|
int opal_paffinity_base_register_params(void)
|
|
{
|
|
int value, id;
|
|
|
|
/* Debugging / verbose output */
|
|
|
|
mca_base_param_reg_int_name("paffinity", "base_verbose",
|
|
"Verbosity level of the paffinity framework",
|
|
false, false,
|
|
0, &value);
|
|
if (0 != value) {
|
|
opal_paffinity_base_output = opal_output_open(NULL);
|
|
} else {
|
|
opal_paffinity_base_output = -1;
|
|
}
|
|
|
|
id = mca_base_param_reg_int_name("opal", "paffinity_alone",
|
|
"If nonzero, assume that this job is the only (set of) process(es) running on each node and bind processes to processors, starting with processor ID 0",
|
|
false, false,
|
|
0, NULL);
|
|
/* register the historical mpi_paffinity_alone synonym, but don't
|
|
* declare it deprecated so we don't scare the users.
|
|
*
|
|
* Yes, this breaks the abstraction barrier, but as indicated
|
|
* on the developer list....live with it. :-)
|
|
*/
|
|
mca_base_param_reg_syn_name(id, "mpi", "paffinity_alone", false);
|
|
mca_base_param_lookup_int(id, &value);
|
|
opal_paffinity_alone = OPAL_INT_TO_BOOL(value);
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|
|
|
|
/*
|
|
* Function for finding and opening either all MCA components, or the one
|
|
* that was specifically requested via a MCA parameter.
|
|
*/
|
|
int opal_paffinity_base_open(void)
|
|
{
|
|
opal_paffinity_base_components_opened_valid = false;
|
|
|
|
mca_base_param_reg_string_name("opal", "paffinity_base_slot_list",
|
|
"Used to set list of processor IDs to bind MPI processes to (e.g., used in conjunction with rank files)",
|
|
true, false, NULL, &opal_paffinity_base_slot_list);
|
|
|
|
/* Open up all available components */
|
|
|
|
if (OPAL_SUCCESS !=
|
|
mca_base_components_open("paffinity", opal_paffinity_base_output,
|
|
mca_paffinity_base_static_components,
|
|
&opal_paffinity_base_components_opened,
|
|
true)) {
|
|
return OPAL_ERROR;
|
|
}
|
|
opal_paffinity_base_components_opened_valid = true;
|
|
|
|
/* All done */
|
|
|
|
return OPAL_SUCCESS;
|
|
}
|