e968ddfe64
* mpi/start: fix bugs in cm and ob1 start functions There were several problems with the implementation of start in Open MPI: - There are no checks whatsoever on the state of the request(s) provided to MPI_Start/MPI_Start_all. It is erroneous to provide an active request to either of these calls. Since we are already looping over the provided requests there is little overhead in verifying that the request can be started. - Both ob1 and cm were always throwing away the request on the initial call to start and start_all with a particular request. Subsequent calls would see that the request was pml_complete and reuse it. This introduced a leak as the initial request was never freed. Since the only pml request that can be mpi complete but not pml complete is a buffered send the code to reallocate the request has been moved. To detect that a request is indeed mpi complete but not pml complete isend_init in both cm and ob1 now marks the new request as pml complete. - If a new request was needed the callbacks on the original request were not copied over to the new request. This can cause osc/pt2pt to hang as the incoming message callback is never called. Signed-off-by: Nathan Hjelm <hjelmn@lanl.gov> * osc/pt2pt: add request for gc after starting a new request Starting a new receive may cause a recursive call into the pt2pt frag receive function. If this happens and the prior request is on the garbage collection list it could cause problems. This commit moves the gc insert until after the new request has been posted. Signed-off-by: Nathan Hjelm <hjelmn@me.com>
98 строки
3.0 KiB
C
98 строки
3.0 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) 2004-2008 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 (c) 2012 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
* Copyright (c) 2014-2015 Research Organization for Information Science
|
|
* and Technology (RIST). All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
#include "ompi_config.h"
|
|
#include <stdio.h>
|
|
|
|
#include "ompi/mpi/c/bindings.h"
|
|
#include "ompi/runtime/params.h"
|
|
#include "ompi/communicator/communicator.h"
|
|
#include "ompi/errhandler/errhandler.h"
|
|
#include "ompi/mca/pml/pml.h"
|
|
#include "ompi/request/request.h"
|
|
#include "ompi/memchecker.h"
|
|
|
|
#if OMPI_BUILD_MPI_PROFILING
|
|
#if OPAL_HAVE_WEAK_SYMBOLS
|
|
#pragma weak MPI_Startall = PMPI_Startall
|
|
#endif
|
|
#define MPI_Startall PMPI_Startall
|
|
#endif
|
|
|
|
static const char FUNC_NAME[] = "MPI_Startall";
|
|
|
|
|
|
int MPI_Startall(int count, MPI_Request requests[])
|
|
{
|
|
int i;
|
|
int ret = OMPI_SUCCESS;
|
|
|
|
MEMCHECKER(
|
|
int j;
|
|
for (j = 0; j < count; j++){
|
|
memchecker_request(&requests[j]);
|
|
}
|
|
);
|
|
|
|
if ( MPI_PARAM_CHECK ) {
|
|
int rc = MPI_SUCCESS;
|
|
OMPI_ERR_INIT_FINALIZE(FUNC_NAME);
|
|
if (NULL == requests) {
|
|
rc = MPI_ERR_REQUEST;
|
|
} else if (count < 0) {
|
|
rc = MPI_ERR_ARG;
|
|
} else {
|
|
for (i = 0; i < count; ++i) {
|
|
if (NULL == requests[i] ||
|
|
(OMPI_REQUEST_PML != requests[i]->req_type &&
|
|
OMPI_REQUEST_NOOP != requests[i]->req_type)) {
|
|
rc = MPI_ERR_REQUEST;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
OMPI_ERRHANDLER_CHECK(rc, MPI_COMM_WORLD, rc, FUNC_NAME);
|
|
}
|
|
|
|
OPAL_CR_ENTER_LIBRARY();
|
|
|
|
for (i = 0; i < count; ++i) {
|
|
if (OMPI_REQUEST_NOOP == requests[i]->req_type) {
|
|
/**
|
|
* We deal with a MPI_PROC_NULL request. If the request is
|
|
* already active, fall back to the error case in the default.
|
|
* Otherwise, mark it active so we can correctly handle it in
|
|
* the wait*.
|
|
*/
|
|
if( OMPI_REQUEST_INACTIVE == requests[i]->req_state ) {
|
|
requests[i]->req_state = OMPI_REQUEST_ACTIVE;
|
|
}
|
|
}
|
|
}
|
|
|
|
ret = MCA_PML_CALL(start(count, requests));
|
|
|
|
OPAL_CR_EXIT_LIBRARY();
|
|
return ret;
|
|
}
|
|
|