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>
109 строки
3.4 KiB
C
109 строки
3.4 KiB
C
/*
|
|
* Copyright (c) 2004-2008 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 Los Alamos National Security, LLC.
|
|
* All rights reserved.
|
|
* Copyright (c) 2017 Intel, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @file:
|
|
*
|
|
* The Open RTE Resource MAPping Subsystem (RMAPS)
|
|
*
|
|
* The resource mapping subsystem is responsible for mapping processes
|
|
* to specific nodes/cpus within a given job. In many systems, this
|
|
* functionality will not be supported - the system will map processes
|
|
* wherever it chooses and does not allow the user to specify the
|
|
* mapping. RMAPS components, therefore, provide services for those
|
|
* systems that do permit such mappings.
|
|
*
|
|
* RMAPS checks the MCA parameters to see if a mapping algorithm has
|
|
* been specified. If the user selected a mapping algorithm, the
|
|
* indicated RMAPS component will take information from the registry
|
|
* to determine the number of applications/processes to be run, and
|
|
* the identified resources that have been allocated to this job. The
|
|
* selected RMAP component will then assign processes to resources
|
|
* according to its algorithm, with the results stored on the
|
|
* appropriate job segment - the assigned nodename for each process is
|
|
* stored in that respective process' container on the segment.
|
|
*
|
|
*/
|
|
|
|
#ifndef ORTE_MCA_RMAPS_H
|
|
#define ORTE_MCA_RMAPS_H
|
|
|
|
#include "orte_config.h"
|
|
#include "orte/types.h"
|
|
|
|
#include "orte/mca/mca.h"
|
|
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
#include "orte/mca/rmaps/rmaps_types.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/*
|
|
* rmaps module functions
|
|
*/
|
|
|
|
/* mapping event - the event one activates to schedule mapping
|
|
* of procs to nodes for pending jobs
|
|
*/
|
|
ORTE_DECLSPEC extern opal_event_t orte_mapping_event;
|
|
|
|
/**
|
|
* RMAPS module functions - these are not accessible to the outside world,
|
|
* but are defined here by convention
|
|
*/
|
|
typedef int (*orte_rmaps_base_module_map_fn_t)(orte_job_t *jdata);
|
|
|
|
/*
|
|
* rmaps module version 3.0.0
|
|
*/
|
|
struct orte_rmaps_base_module_3_0_0_t {
|
|
/** Mapping function pointer */
|
|
orte_rmaps_base_module_map_fn_t map_job;
|
|
};
|
|
/** Convenience typedef */
|
|
typedef struct orte_rmaps_base_module_3_0_0_t orte_rmaps_base_module_3_0_0_t;
|
|
/** Convenience typedef */
|
|
typedef orte_rmaps_base_module_3_0_0_t orte_rmaps_base_module_t;
|
|
|
|
|
|
/*
|
|
* rmaps component
|
|
*/
|
|
|
|
/**
|
|
* rmaps component version 3.0.0
|
|
*/
|
|
struct orte_rmaps_base_component_3_0_0_t {
|
|
/** Base MCA structure */
|
|
mca_base_component_t base_version;
|
|
/** Base MCA data */
|
|
mca_base_component_data_t base_data;
|
|
};
|
|
/** Convenience typedef */
|
|
typedef struct orte_rmaps_base_component_3_0_0_t orte_rmaps_base_component_3_0_0_t;
|
|
/** Convenience typedef */
|
|
typedef orte_rmaps_base_component_3_0_0_t orte_rmaps_base_component_t;
|
|
|
|
|
|
END_C_DECLS
|
|
|
|
#endif
|