657e701c65
Start updating the various mappers to the new procedure. Remove the stale lama component as it is now very out-of-date. Bring round_robin and PPR online, and modify the mindist component (but cannot test/debug it). Remove unneeded test Fix memory corruption by re-initializing variable to NULL in loop Resolve the race condition identified by @ggouaillardet by resetting the mapped flag within the same event where it was set. There is no need to retain the flag beyond that point as it isn't used again. Add a new job attribute ORTE_JOB_FULLY_DESCRIBED to indicate that all the job information (including locations and binding) is included in the launch message. Thus, the backend daemons do not need to do any map computation for the job. Use this for the seq, rankfile, and mindist mappers until someone decides to update them. Note that this will maintain functionality, but means that users of those three mappers will see large launch messages and less performant scaling than those using the other mappers. Have the mindist module add procs to the job's proc array as it is a fully described module Protect the hnp-not-in-allocation case Per path suggested by Gilles - protect the HNP node when it gets added in the absence of any other allocation or hostfile Signed-off-by: Ralph Castain <rhc@open-mpi.org>
135 строки
4.0 KiB
C
135 строки
4.0 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 (c) 2011 Cisco Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2011-2013 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* Copyright (c) 2014-2017 Intel, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @file:
|
|
* rmaps framework base functionality.
|
|
*/
|
|
|
|
#ifndef ORTE_MCA_RMAPS_BASE_H
|
|
#define ORTE_MCA_RMAPS_BASE_H
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
#include "orte/types.h"
|
|
|
|
#include "opal/class/opal_list.h"
|
|
#include "orte/mca/mca.h"
|
|
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
#include "orte/mca/rmaps/rmaps.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/*
|
|
* MCA Framework
|
|
*/
|
|
ORTE_DECLSPEC extern mca_base_framework_t orte_rmaps_base_framework;
|
|
/* select a component */
|
|
ORTE_DECLSPEC int orte_rmaps_base_select(void);
|
|
|
|
/*
|
|
* Global functions for MCA overall collective open and close
|
|
*/
|
|
|
|
/**
|
|
* Struct to hold data global to the rmaps framework
|
|
*/
|
|
typedef struct {
|
|
/* list of selected modules */
|
|
opal_list_t selected_modules;
|
|
/* default ppr */
|
|
char *ppr;
|
|
/* cpus per rank */
|
|
int cpus_per_rank;
|
|
/* display the map after it is computed */
|
|
bool display_map;
|
|
/* slot list, if provided by user */
|
|
char *slot_list;
|
|
/* default mapping directives */
|
|
orte_mapping_policy_t mapping;
|
|
orte_ranking_policy_t ranking;
|
|
/* device specification for min distance mapping */
|
|
char *device;
|
|
} orte_rmaps_base_t;
|
|
|
|
/**
|
|
* Global instance of rmaps-wide framework data
|
|
*/
|
|
ORTE_DECLSPEC extern orte_rmaps_base_t orte_rmaps_base;
|
|
|
|
/**
|
|
* Global MCA variables
|
|
*/
|
|
ORTE_DECLSPEC extern bool orte_rmaps_base_pernode;
|
|
ORTE_DECLSPEC extern int orte_rmaps_base_n_pernode;
|
|
ORTE_DECLSPEC extern int orte_rmaps_base_n_persocket;
|
|
|
|
/**
|
|
* Select an rmaps component / module
|
|
*/
|
|
typedef struct {
|
|
opal_list_item_t super;
|
|
int pri;
|
|
orte_rmaps_base_module_t *module;
|
|
mca_base_component_t *component;
|
|
} orte_rmaps_base_selected_module_t;
|
|
OBJ_CLASS_DECLARATION(orte_rmaps_base_selected_module_t);
|
|
|
|
/*
|
|
* Map a job
|
|
*/
|
|
ORTE_DECLSPEC void orte_rmaps_base_map_job(int sd, short args, void *cbdata);
|
|
ORTE_DECLSPEC int orte_rmaps_base_assign_locations(orte_job_t *jdata);
|
|
|
|
/**
|
|
* Utility routines to get/set vpid mapping for the job
|
|
*/
|
|
|
|
ORTE_DECLSPEC int orte_rmaps_base_get_vpid_range(orte_jobid_t jobid,
|
|
orte_vpid_t *start, orte_vpid_t *range);
|
|
ORTE_DECLSPEC int orte_rmaps_base_set_vpid_range(orte_jobid_t jobid,
|
|
orte_vpid_t start, orte_vpid_t range);
|
|
|
|
/* pretty-print functions */
|
|
ORTE_DECLSPEC char* orte_rmaps_base_print_mapping(orte_mapping_policy_t mapping);
|
|
ORTE_DECLSPEC char* orte_rmaps_base_print_ranking(orte_ranking_policy_t ranking);
|
|
|
|
ORTE_DECLSPEC int orte_rmaps_base_prep_topology(hwloc_topology_t topo);
|
|
|
|
ORTE_DECLSPEC int orte_rmaps_base_filter_nodes(orte_app_context_t *app,
|
|
opal_list_t *nodes,
|
|
bool remove);
|
|
|
|
ORTE_DECLSPEC int orte_rmaps_base_set_mapping_policy(orte_mapping_policy_t *policy,
|
|
char **device, char *spec);
|
|
ORTE_DECLSPEC int orte_rmaps_base_set_ranking_policy(orte_ranking_policy_t *policy,
|
|
orte_mapping_policy_t mapping,
|
|
char *spec);
|
|
|
|
ORTE_DECLSPEC void orte_rmaps_base_display_map(orte_job_t *jdata);
|
|
|
|
END_C_DECLS
|
|
|
|
#endif
|