48fc339718
onto the backend daemons. By default, let mpirun only pack the app_context info and send that to the backend daemons where the mapping will be done. This significantly reduces the computational time on mpirun as it isn't running up/down the topology tree computing thousands of binding locations, and it reduces the launch message to a very small number of bytes. When running -novm, fall back to the old way of doing things where mpirun computes the entire map and binding, and then sends the full info to the backend daemon. Add a new cmd line option/mca param --fwd-mpirun-port that allows mpirun to dynamically select a port, but then passes that back to all the other daemons so they will use that port as a static port for their own wireup. In this mode, we no longer "phone home" directly to mpirun, but instead use the static port to wireup at daemon start. We then use the routing tree to rollup the initial launch report, and limit the number of open sockets on mpirun's node. Update ras simulator to track the new nidmap code Cleanup some bugs in the nidmap regex code, and enhance the error message for not enough slots to include the host on which the problem is found. Update gadget platform file Initialize the range count when starting a new range Fix the no-np case in managed allocation Ensure DVM node usage gets cleaned up after each job Update scaling.pl script to use --fwd-mpirun-port. Pre-connect the daemon to its parent during launch while we are otherwise waiting for the daemon's children to send their "phone home" rollup messages Signed-off-by: Ralph Castain <rhc@open-mpi.org>
134 строки
3.9 KiB
C
134 строки
3.9 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 int orte_rmaps_base_map_job(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
|