f11931306a
Correct an error wrt how jobids were being computed. Needed to ensure that the job family field was not overrun as we increment jobids for comm_spawn. Update the slurm plm module so it uses the new slurm termination procedure (brings trunk back into alignment with 1.3 branch). Update the slurmd ess component so it doesn't get selected if we are running a singleton inside of a slurm allocation. Cleanup HNP init by moving some code that had been in orte_globals.c for historical reasons into the ess hnp module, and removing the call to that code from the ess_base_std_prolog NOTE: this change allows orte to support an infinite aggregate number of comm_spawn's, with up to 64k being alive at any one instant. HOWEVER, the MPI layer currently does -not- support re-use of jobids. I did some prototype coding to revise the ompi_proc_t structures, but the BTLs are caching their own data, and there was no readily apparent way to update it. Thus, attempts to spawn more than the 64k limit will abort to avoid causing the MPI layer to hang. This commit was SVN r20700.
99 строки
2.7 KiB
C
99 строки
2.7 KiB
C
/*
|
|
* Copyright (c) 2004-2008 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.
|
|
* $COPYRIGHT$
|
|
*
|
|
* 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 "orte/util/proc_info.h"
|
|
|
|
#include "orte/mca/ess/ess.h"
|
|
#include "orte/mca/ess/slurmd/ess_slurmd.h"
|
|
|
|
extern orte_ess_base_module_t orte_ess_slurmd_module;
|
|
|
|
/*
|
|
* Instantiate the public struct with all of our public information
|
|
* and pointers to our public functions in it
|
|
*/
|
|
orte_ess_base_component_t mca_ess_slurmd_component = {
|
|
{
|
|
ORTE_ESS_BASE_VERSION_2_0_0,
|
|
|
|
/* Component name and version */
|
|
"slurmd",
|
|
ORTE_MAJOR_VERSION,
|
|
ORTE_MINOR_VERSION,
|
|
ORTE_RELEASE_VERSION,
|
|
|
|
/* Component open and close functions */
|
|
orte_ess_slurmd_component_open,
|
|
orte_ess_slurmd_component_close,
|
|
orte_ess_slurmd_component_query
|
|
},
|
|
{
|
|
/* The component is checkpoint ready */
|
|
MCA_BASE_METADATA_PARAM_CHECKPOINT
|
|
}
|
|
};
|
|
|
|
|
|
int
|
|
orte_ess_slurmd_component_open(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
int orte_ess_slurmd_component_query(mca_base_module_t **module, int *priority)
|
|
{
|
|
/* Are we an MPI proc running under a SLURM job? Were
|
|
* we given a path back to the HNP? If the
|
|
* answer to the first is "yes" and the second
|
|
* is "no", then we were not launched
|
|
* by mpirun but are in a slurm world
|
|
*/
|
|
|
|
if (orte_process_info.mpi_proc &&
|
|
NULL != getenv("SLURM_JOBID") &&
|
|
NULL != getenv("SLURM_STEPID") &&
|
|
NULL == orte_process_info.my_hnp_uri) {
|
|
*priority = 30;
|
|
*module = (mca_base_module_t *)&orte_ess_slurmd_module;
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
/* Sadly, no */
|
|
*priority = -1;
|
|
*module = NULL;
|
|
return ORTE_ERROR;
|
|
}
|
|
|
|
|
|
int
|
|
orte_ess_slurmd_component_close(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|