497c7e6abb
The intercomm "merge" function can create a linkage between procs that was not reflected anywhere in a modex, and so at least some of the procs in the resulting communicator don't know how to talk to some of the new communicator's peers. For example, consider the case where: 1. parent job A comm_spawns a process (job B) - these processes exchange modex and can communicate 2. parent job A now comm_spawns another process (job C) - again, these can communicate, but the proc in C knows nothing of B 3. do an intercomm merge across the communicators created by the two comm_spawns. This puts B and C into the same communicator, but they know nothing about how to talk to each other as they were not involved in any exchange of contact info. Hence, collectives on that communicator now fail. This fix adds an API to the ompi/dpm framework that (a) exchanges the modex info across the procs in the merge to ensure all procs know how to communicate, and (b) calls add_procs to give the btl's a chance to select transports to any new procs. cmr:v1.7.3:reviewer=jsquyres This commit was SVN r29166. The following Trac tickets were found above: Ticket 2904 --> https://svn.open-mpi.org/trac/ompi/ticket/2904
65 строки
1.9 KiB
C
65 строки
1.9 KiB
C
/*
|
|
* Copyright (c) 2004-2007 The Trustees of Indiana University.
|
|
* All rights reserved.
|
|
* Copyright (c) 2004-2005 The Trustees of the University of Tennessee.
|
|
* 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) 2013 Intel, Inc. All rights reserved
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "ompi_config.h"
|
|
|
|
#include "opal/mca/mca.h"
|
|
#include "opal/util/output.h"
|
|
#include "opal/mca/base/base.h"
|
|
|
|
#include "ompi/mca/dpm/dpm.h"
|
|
#include "ompi/mca/dpm/base/base.h"
|
|
|
|
#include "ompi/mca/dpm/base/static-components.h"
|
|
|
|
/*
|
|
* Globals
|
|
*/
|
|
OMPI_DECLSPEC ompi_dpm_base_module_t ompi_dpm = {
|
|
NULL,
|
|
ompi_dpm_base_null_connect_accept,
|
|
ompi_dpm_base_null_merge,
|
|
ompi_dpm_base_null_disconnect,
|
|
ompi_dpm_base_null_spawn,
|
|
ompi_dpm_base_null_dyn_init,
|
|
ompi_dpm_base_null_dyn_finalize,
|
|
ompi_dpm_base_null_mark_dyncomm,
|
|
ompi_dpm_base_null_open_port,
|
|
ompi_dpm_base_null_parse_port,
|
|
ompi_dpm_base_null_route_to_port,
|
|
ompi_dpm_base_null_close_port,
|
|
NULL,
|
|
ompi_dpm_base_null_pconnect,
|
|
ompi_dpm_base_null_paccept,
|
|
ompi_dpm_base_null_pclose
|
|
};
|
|
ompi_dpm_base_component_t ompi_dpm_base_selected_component;
|
|
|
|
static int ompi_dpm_base_close(void)
|
|
{
|
|
/* Close the selected component */
|
|
if( NULL != ompi_dpm.finalize ) {
|
|
ompi_dpm.finalize();
|
|
}
|
|
|
|
/* Close all available modules that are open */
|
|
return mca_base_framework_components_close(&ompi_dpm_base_framework, NULL);
|
|
}
|
|
|
|
MCA_BASE_FRAMEWORK_DECLARE(ompi, dpm, NULL, NULL, NULL, ompi_dpm_base_close,
|
|
mca_dpm_base_static_components, 0);
|