2005-03-14 23:57:21 +03:00
/*
2007-03-17 02:11:45 +03:00
* Copyright ( c ) 2004 - 2007 The Trustees of Indiana University and Indiana
2005-11-05 22:57:48 +03:00
* 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 .
2005-03-14 23:57:21 +03:00
* Copyright ( c ) 2004 - 2005 High Performance Computing Center Stuttgart ,
* University of Stuttgart . All rights reserved .
2005-03-24 15:43:37 +03:00
* Copyright ( c ) 2004 - 2005 The Regents of the University of California .
* All rights reserved .
2006-07-05 00:12:35 +04:00
* Copyright ( c ) 2006 Cisco Systems , Inc . All rights reserved .
2005-03-14 23:57:21 +03:00
* $ 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 .
*/
2006-02-12 04:33:29 +03:00
# include "orte_config.h"
2008-02-28 04:57:57 +03:00
# include "orte/constants.h"
2005-03-14 23:57:21 +03:00
2005-08-25 02:20:51 +04:00
# include "opal/mca/base/mca_base_param.h"
2005-09-10 14:39:15 +04:00
# include "opal/util/output.h"
2005-10-04 23:38:51 +04:00
# include "opal/util/argv.h"
2006-09-15 01:29:51 +04:00
# include "orte/util/proc_info.h"
# include "orte/mca/errmgr/errmgr.h"
2008-02-28 04:57:57 +03:00
# include "orte/mca/plm/plm.h"
# include "orte/mca/plm/base/base.h"
# include "orte/mca/plm/base/plm_private.h"
# include "plm_tm.h"
2005-03-14 23:57:21 +03:00
/*
2008-02-28 04:57:57 +03:00
* Public string showing the plm ompi_tm component version number
2005-03-14 23:57:21 +03:00
*/
2008-02-28 04:57:57 +03:00
const char * mca_plm_tm_component_version_string =
" Open MPI tm plm MCA component version " ORTE_VERSION ;
2005-03-14 23:57:21 +03:00
/*
* Local function
*/
2008-02-28 04:57:57 +03:00
static int plm_tm_open ( void ) ;
static int plm_tm_close ( void ) ;
static orte_plm_base_module_t * plm_tm_init ( int * priority ) ;
2005-03-14 23:57:21 +03:00
/*
* Instantiate the public struct with all of our public information
* and pointers to our public functions in it
*/
2008-02-28 04:57:57 +03:00
orte_plm_tm_component_t mca_plm_tm_component = {
2005-03-14 23:57:21 +03:00
{
2005-08-19 20:49:59 +04:00
/* First, the mca_component_t struct containing meta information
about the component itself */
{
2008-02-28 04:57:57 +03:00
/* Indicate that we are a plm v1.0.0 component (which also
2005-08-19 20:49:59 +04:00
implies a specific MCA version ) */
2008-02-28 04:57:57 +03:00
ORTE_PLM_BASE_VERSION_1_0_0 ,
2005-08-19 20:49:59 +04:00
/* Component name and version */
" tm " ,
ORTE_MAJOR_VERSION ,
ORTE_MINOR_VERSION ,
ORTE_RELEASE_VERSION ,
/* Component open and close functions */
2008-02-28 04:57:57 +03:00
plm_tm_open ,
plm_tm_close ,
2005-08-19 20:49:59 +04:00
} ,
/* Next the MCA v1.0.0 component meta data */
{
2007-03-17 02:11:45 +03:00
/* The component is checkpoint ready */
MCA_BASE_METADATA_PARAM_CHECKPOINT
2005-08-19 20:49:59 +04:00
} ,
/* Initialization / querying functions */
2008-02-28 04:57:57 +03:00
plm_tm_init
2005-08-19 20:49:59 +04:00
}
2005-03-14 23:57:21 +03:00
} ;
2008-02-28 04:57:57 +03:00
static int plm_tm_open ( void )
2005-03-14 23:57:21 +03:00
{
2008-02-28 04:57:57 +03:00
int tmp ;
mca_base_component_t * comp = & mca_plm_tm_component . super . plm_version ;
2005-08-19 20:49:59 +04:00
2005-10-04 23:38:51 +04:00
mca_base_param_reg_string ( comp , " orted " ,
" Command to use to start proxy orted " ,
false , false , " orted " ,
2008-02-28 04:57:57 +03:00
& mca_plm_tm_component . orted ) ;
2005-10-04 23:38:51 +04:00
mca_base_param_reg_int ( comp , " want_path_check " ,
2008-02-28 04:57:57 +03:00
" Whether the launching process should check for the plm_tm_orted executable in the PATH before launching (the TM API does not give an idication of failure; this is a somewhat-lame workaround; non-zero values enable this check) " ,
2005-10-04 23:38:51 +04:00
false , false , ( int ) true , & tmp ) ;
2008-02-28 04:57:57 +03:00
mca_plm_tm_component . want_path_check = OPAL_INT_TO_BOOL ( tmp ) ;
Bring the timing instrumentation to the trunk.
If you want to look at our launch and MPI process startup times, you can do so with two MCA params:
OMPI_MCA_orte_timing: set it to anything non-zero and you will get the launch time for different steps in the job launch procedure. The degree of detail depends on the launch environment. rsh will provide you with the average, min, and max launch time for the daemons. SLURM block launches the daemon, so you only get the time to launch the daemons and the total time to launch the job. Ditto for bproc. TM looks more like rsh. Only those four environments are currently supported - anyone interested in extending this capability to other environs is welcome to do so. In all cases, you also get the time to setup the job for launch.
OMPI_MCA_ompi_timing: set it to anything non-zero and you will get the time for mpi_init to reach the compound registry command, the time to execute that command, the time to go from our stage1 barrier to the stage2 barrier, and the time to go from the stage2 barrier to the end of mpi_init. This will be output for each process, so you'll have to compile any statistics on your own. Note: if someone develops a nice parser to do so, it would be really appreciated if you could/would share!
This commit was SVN r12302.
2006-10-25 19:27:47 +04:00
2008-02-28 04:57:57 +03:00
mca_plm_tm_component . checked_paths = NULL ;
2005-10-04 23:38:51 +04:00
return ORTE_SUCCESS ;
}
2008-02-28 04:57:57 +03:00
static int plm_tm_close ( void )
2005-10-04 23:38:51 +04:00
{
2008-02-28 04:57:57 +03:00
if ( NULL ! = mca_plm_tm_component . checked_paths ) {
opal_argv_free ( mca_plm_tm_component . checked_paths ) ;
2005-10-04 23:38:51 +04:00
}
2005-03-14 23:57:21 +03:00
return ORTE_SUCCESS ;
}
2008-02-28 04:57:57 +03:00
static orte_plm_base_module_t * plm_tm_init ( int * priority )
2005-03-14 23:57:21 +03:00
{
/* Are we running under a TM job? */
if ( NULL ! = getenv ( " PBS_ENVIRONMENT " ) & &
NULL ! = getenv ( " PBS_JOBID " ) ) {
2006-09-15 01:29:51 +04:00
2008-02-28 04:57:57 +03:00
* priority = 75 ;
return & orte_plm_tm_module ;
2005-03-14 23:57:21 +03:00
}
/* Sadly, no */
return NULL ;
}