a62b2a0150
Standardize the handling of the orte launch agent option across PLMs. This has been a consistent complaint I have received - each PLM would register its own MCA param to get input on the launch agent for remote nodes (in fact, one or two didn't, but most did). This would then get handled in various and contradictory ways. Some PLMs would accept only a one-word input. Others accepted multi-word args such as "valgrind orted", but then some would error by putting any prefix specified on the cmd line in front of the incorrect argument. For example, while using the rsh launcher, if you specified "valgrind orted" as your launch agent and had "--prefix foo" on you cmd line, you would attempt to execute "ssh foo/valgrind orted" - which obviously wouldn't work. This was all -very- confusing to users, who had to know which PLM was being used so they could even set the right mca param in the first place! And since we don't warn about non-recognized or non-used mca params, half of the time they would wind up not doing what they thought they were telling us to do. To solve this problem, we did the following: 1. removed all mca params from the individual plms for the launch agent 2. added a new mca param "orte_launch_agent" for this purpose. To further simplify for users, this comes with a new cmd line option "--launch-agent" that can take a multi-word string argument. The value of the param defaults to "orted". 3. added a PLM base function that processes the orte_launch_agent value and adds the contents to a provided argv array. This can subsequently be harvested at-will to handle multi-word values 4. modified the PLMs to use this new function. All the PLMs except for the rsh PLM required very minor change - just called the function and moved on. The rsh PLM required much larger changes as - because of the rsh/ssh cmd line limitations - we had to correctly prepend any provided prefix to the correct argv entry. 5. added a new opal_argv_join_range function that allows the caller to "join" argv entries between two specified indices Please let me know of any problems. I tried to make this as clean as possible, but cannot compile all PLMs to ensure all is correct. This commit was SVN r19097.
122 строки
3.4 KiB
C
122 строки
3.4 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 (c) 2006-2007 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2008 Institut National de Recherche en Informatique
|
|
* et Automatique. 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 <lsf/lsbatch.h>
|
|
|
|
#include "opal/mca/base/mca_base_param.h"
|
|
#include "opal/util/argv.h"
|
|
|
|
#include "orte/util/show_help.h"
|
|
#include "orte/util/proc_info.h"
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
|
|
#include "orte/mca/plm/plm.h"
|
|
#include "orte/mca/plm/base/base.h"
|
|
#include "orte/mca/plm/base/plm_private.h"
|
|
#include "plm_lsf.h"
|
|
|
|
|
|
/*
|
|
* Public string showing the plm lsf component version number
|
|
*/
|
|
const char *mca_plm_lsf_component_version_string =
|
|
"Open MPI lsf plm MCA component version " ORTE_VERSION;
|
|
|
|
|
|
|
|
/*
|
|
* Local function
|
|
*/
|
|
static int plm_lsf_open(void);
|
|
static int plm_lsf_close(void);
|
|
static int orte_plm_lsf_component_query(mca_base_module_t **module, int *priority);
|
|
|
|
|
|
/*
|
|
* Instantiate the public struct with all of our public information
|
|
* and pointers to our public functions in it
|
|
*/
|
|
|
|
orte_plm_lsf_component_t mca_plm_lsf_component = {
|
|
{
|
|
/* First, the mca_component_t struct containing meta information
|
|
about the component itself */
|
|
|
|
{
|
|
ORTE_PLM_BASE_VERSION_2_0_0,
|
|
|
|
/* Component name and version */
|
|
"lsf",
|
|
ORTE_MAJOR_VERSION,
|
|
ORTE_MINOR_VERSION,
|
|
ORTE_RELEASE_VERSION,
|
|
|
|
/* Component open and close functions */
|
|
plm_lsf_open,
|
|
plm_lsf_close,
|
|
orte_plm_lsf_component_query
|
|
},
|
|
{
|
|
/* The component is checkpoint ready */
|
|
MCA_BASE_METADATA_PARAM_CHECKPOINT
|
|
}
|
|
}
|
|
};
|
|
|
|
|
|
static int plm_lsf_open(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
static int plm_lsf_close(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
|
|
static int orte_plm_lsf_component_query(mca_base_module_t **module, int *priority)
|
|
{
|
|
|
|
/* check if lsf is running here */
|
|
if (NULL == getenv("LSB_JOBID") || lsb_init("ORTE launcher") < 0) {
|
|
/* nope, not here */
|
|
opal_output_verbose(10, orte_plm_globals.output,
|
|
"plm:lsf: NOT available for selection");
|
|
*module = NULL;
|
|
return ORTE_ERROR;
|
|
}
|
|
|
|
*priority = 75;
|
|
*module = (mca_base_module_t *) &orte_plm_lsf_module;
|
|
return ORTE_SUCCESS;
|
|
}
|