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>
85 строки
2.2 KiB
C
85 строки
2.2 KiB
C
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
|
|
/*
|
|
* Copyright (c) 2011-2015 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
*
|
|
* Copyright (c) 2017 Intel, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "orte_config.h"
|
|
#include "opal/util/output.h"
|
|
|
|
#include "orte/runtime/orte_globals.h"
|
|
#include "orte/mca/state/state.h"
|
|
#include "orte/mca/state/base/base.h"
|
|
#include "state_novm.h"
|
|
|
|
/*
|
|
* Public string for version number
|
|
*/
|
|
const char *orte_state_novm_component_version_string =
|
|
"ORTE STATE novm MCA component version " ORTE_VERSION;
|
|
|
|
/*
|
|
* Local functionality
|
|
*/
|
|
static int state_novm_open(void);
|
|
static int state_novm_close(void);
|
|
static int state_novm_component_query(mca_base_module_t **module, int *priority);
|
|
|
|
/*
|
|
* Instantiate the public struct with all of our public information
|
|
* and pointer to our public functions in it
|
|
*/
|
|
orte_state_base_component_t mca_state_novm_component =
|
|
{
|
|
/* Handle the general mca_component_t struct containing
|
|
* meta information about the component
|
|
*/
|
|
.base_version = {
|
|
ORTE_STATE_BASE_VERSION_1_0_0,
|
|
/* Component name and version */
|
|
.mca_component_name = "novm",
|
|
MCA_BASE_MAKE_VERSION(component, ORTE_MAJOR_VERSION, ORTE_MINOR_VERSION,
|
|
ORTE_RELEASE_VERSION),
|
|
|
|
/* Component open and close functions */
|
|
.mca_open_component = state_novm_open,
|
|
.mca_close_component = state_novm_close,
|
|
.mca_query_component = state_novm_component_query
|
|
},
|
|
.base_data = {
|
|
/* The component is checkpoint ready */
|
|
MCA_BASE_METADATA_PARAM_CHECKPOINT
|
|
},
|
|
};
|
|
|
|
static int state_novm_open(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
static int state_novm_close(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
static int state_novm_component_query(mca_base_module_t **module, int *priority)
|
|
{
|
|
if (ORTE_PROC_IS_HNP && orte_no_vm) {
|
|
/* set our priority high so we'll be selected if user desires */
|
|
*priority = 1000;
|
|
*module = (mca_base_module_t *)&orte_state_novm_module;
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
*priority = -1;
|
|
*module = NULL;
|
|
return ORTE_ERROR;
|
|
}
|