1
1
openmpi/ompi/mpi/c/group_free.c
Josh Hursey 99144db970 Improve checkpoint/restart support by allowing a checkpoint to progress when the process is *not* in the MPI library. This involves creating a separate thread for polling for a checkpoint request. This thread is active when the MPI process is not in the MPI library, and paused when the MPI process is in the library.
Some MPI C interface files saw some spacing changes to conform to the coding standards of Open MPI.

Changed MPI C interface files to use {{{OPAL_CR_ENTER_LIBRARY()}}} and {{{OPAL_CR_EXIT_LIBRARY()}}} instead of just {{{OPAL_CR_TEST_CHECKPOINT_READY()}}}. This will allow the checkpoint/restart system more flexibility in how it is to behave.

Fixed the configure check for {{{--enable-ft-thread}}} so it has a know dependance on {{{--enable-mpi-thread}}} (and/or {{{--enable-progress-thread}}}).

Added a line for Checkpoint/Restart support to {{{ompi_info}}}.

Added some options to choose at runtime whether or not to use the checkpoint polling thread. By default, if the user asked for it to be compiled in, then it is used. But some users will want the ability to toggle its use at runtime.

There are still some places for improvement, but the feature works correctly. As always with Checkpoint/Restart, it is compiled out unless explicitly asked for at configure time. Further, if it was configured in, then it is not used unless explicitly asked for by the user at runtime.

This commit was SVN r17516.
2008-02-19 22:15:52 +00:00

73 строки
2.4 KiB
C

/*
* Copyright (c) 2004-2007 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) 2006 Cisco Systems, Inc. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
#include "ompi_config.h"
#include <stdio.h>
#include "ompi/mpi/c/bindings.h"
#include "ompi/group/group.h"
#if OMPI_HAVE_WEAK_SYMBOLS && OMPI_PROFILING_DEFINES
#pragma weak MPI_Group_free = PMPI_Group_free
#endif
#if OMPI_PROFILING_DEFINES
#include "ompi/mpi/c/profile/defines.h"
#endif
static const char FUNC_NAME[] = "MPI_Group_free";
int MPI_Group_free(MPI_Group *group)
{
int ret;
/* check to make sure we don't free GROUP_NULL. Note that we *do*
allow freeing GROUP_EMPTY after much debate in the OMPI core
group. The final thread about this, and the decision to
support freeing GROUP_EMPTY can be found here:
http://www.open-mpi.org/community/lists/devel/2007/12/2750.php
The short version: other MPI's allow it (LAM/MPI, CT6, MPICH2)
probably mainly because the Intel MPI test suite expects it to
happen and there's now several years worth of expected behavior
to allow this behavior. Rather than have to explain every time
why OMPI is the only one who completely adheres to the standard
/ fails the intel tests, it seemed easier to just let this one
slide. It's not really that important, after all! */
if (MPI_PARAM_CHECK) {
OMPI_ERR_INIT_FINALIZE(FUNC_NAME);
if ((NULL == group) ||
(MPI_GROUP_NULL == *group) || (NULL == *group) ) {
return OMPI_ERRHANDLER_INVOKE(MPI_COMM_WORLD, MPI_ERR_GROUP,
FUNC_NAME);
}
}
OPAL_CR_ENTER_LIBRARY();
ret = ompi_group_free ( group);
OMPI_ERRHANDLER_CHECK(ret, MPI_COMM_WORLD, ret, FUNC_NAME);
OPAL_CR_EXIT_LIBRARY();
return MPI_SUCCESS;
}