13227e36ab
Fix the problem observed by multiple people that comm_spawned children were (once again) being mapped onto the same nodes as their parents. This was caused by going through the RAS a second time, thus overwriting the mapper's bookkeeping that told RMAPS where it had left off. To solve this - and to continue moving forward on the ORTE development - we introduce the concept of attributes to control the behavior of the RM frameworks. I defined the attributes and a list of attributes as new ORTE data types to make it easier for people to pass them around (since they are now fundamental to the system, and therefore we will be packing and unpacking them frequently). Thus, all the functions to manipulate attributes can be implemented and debugged in one place. I used those capabilities in two places: 1. Added an attribute list to the rmgr.spawn interface. 2. Added an attribute list to the ras.allocate interface. At the moment, the only attribute I modified the various RAS components to recognize is the USE_PARENT_ALLOCATION one (as defined in rmgr_types.h). So the RAS components now know how to reuse an allocation. I have debugged this under rsh, but it now needs to be tested on a wider set of platforms. This commit was SVN r12138.
60 строки
1.5 KiB
C
60 строки
1.5 KiB
C
/*
|
|
* Copyright (c) 2004-2005 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
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @file:
|
|
*
|
|
*/
|
|
|
|
#include "orte_config.h"
|
|
|
|
#include "orte/orte_constants.h"
|
|
#include "opal/mca/mca.h"
|
|
#include "orte/mca/rmgr/base/rmgr_private.h"
|
|
|
|
|
|
/*
|
|
* "not available" functions
|
|
*/
|
|
int
|
|
orte_rmgr_base_create_not_available(
|
|
orte_app_context_t** app_context,
|
|
orte_std_cntr_t num_context,
|
|
orte_jobid_t* jobid)
|
|
{
|
|
return ORTE_ERR_UNREACH;
|
|
}
|
|
|
|
int
|
|
orte_rmgr_base_spawn_not_available(
|
|
orte_app_context_t** app_context,
|
|
orte_std_cntr_t num_context,
|
|
orte_jobid_t* jobid,
|
|
orte_std_cntr_t num_connect,
|
|
orte_process_name_t *connect,
|
|
orte_rmgr_cb_fn_t cbfn,
|
|
orte_proc_state_t cb_conditions,
|
|
opal_list_t *attributes)
|
|
{
|
|
return ORTE_ERR_UNREACH;
|
|
}
|
|
|
|
int
|
|
orte_rmgr_base_finalize_not_available(void)
|
|
{
|
|
return ORTE_ERR_UNREACH;
|
|
}
|