1
1
openmpi/orte/mca/ras/base/base.h

72 строки
1.8 KiB
C
Исходник Обычный вид История

/*
* 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 (c) 2011-2012 Los Alamos National Security, LLC. All rights
* reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*/
/** @file:
*/
#ifndef ORTE_MCA_RAS_BASE_H
#define ORTE_MCA_RAS_BASE_H
/*
* includes
*/
#include "orte_config.h"
This patch fixes several issues relating to comm_spawn and N1GE. In particular, it does the following: 1. Modifies the RAS framework so it correctly stores and retrieves the actual slots in use, not just those that were allocated. Although the RAS node structure had storage for the number of slots in use, it turned out that the base function for storing and retrieving that information ignored what was in the field and simply set it equal to the number of slots allocated. This has now been fixed. 2. Modified the RMAPS framework so it updates the registry with the actual number of slots used by the mapping. Note that daemons are still NOT counted in this process as daemons are NOT mapped at this time. This will be fixed in 2.0, but will not be addressed in 1.x. 3. Added a new MCA parameter "rmaps_base_no_oversubscribe" that tells the system not to oversubscribe nodes even if the underlying environment permits it. The default is to oversubscribe if needed and the underlying environment permits it. I'm sure someone may argue "why would a user do that?", but it turns out that (looking ahead to dynamic resource reservations) sometimes users won't know how many nodes or slots they've been given in advance - this just allows them to say "hey, I'd rather not run if I didn't get enough". 4. Reorganizes the RMAPS framework to more easily support multiple components. A lot of the logic in the round_robin mapper was very valuable to any component - this has been moved to the base so others can take advantage of it. 5. Added a new test program "hello_nodename" - just does "hello_world" but also prints out the name of the node it is on. 6. Made the orte_ras_node_t object a full ORTE data type so it can more easily be copied, packed, etc. This proved helpful for the RMAPS code reorganization and might be of use elsewhere too. This commit was SVN r10697.
2006-07-10 18:10:21 +04:00
#include "orte/mca/ras/ras.h"
/*
* Global functions for MCA overall collective open and close
*/
BEGIN_C_DECLS
ORTE_DECLSPEC int orte_ras_base_open(void);
#if !ORTE_DISABLE_FULL_SUPPORT
/*
* globals that might be needed
*/
typedef struct orte_ras_base_t {
int ras_output;
opal_list_t ras_opened;
bool allocation_read;
orte_ras_base_module_t *active_module;
int total_slots_alloc;
} orte_ras_base_t;
ORTE_DECLSPEC extern orte_ras_base_t orte_ras_base;
/*
* function definitions
*/
ORTE_DECLSPEC int orte_ras_base_select(void);
ORTE_DECLSPEC int orte_ras_base_finalize(void);
ORTE_DECLSPEC int orte_ras_base_close(void);
ORTE_DECLSPEC void orte_ras_base_display_alloc(void);
ORTE_DECLSPEC void orte_ras_base_allocate(int fd, short args, void *cbdata);
ORTE_DECLSPEC int orte_ras_base_add_hosts(orte_job_t *jdata);
#endif /* ORTE_DISABLE_FULL_SUPPORT */
END_C_DECLS
#endif