1
1
openmpi/orte/mca/ess/singleton/ess_singleton_component.c
Ralph Castain 011403c04a Fix a number of issues, some of which have lingered for a long time:
* provide a more reliable way of determining that a process is a singleton by leveraging the schizo framework. Add new components for slurm, alps, and orte to detect when we are in a managed environment, and if we have been launched by mpirun or a native launcher. Set the correct envars to control ess and pmix selection in each case.

* change the relative priority of the pmix120 and pmix112 components to make pmix120 the default

* fix singleton comm-spawn by correctly setting the num_apps field of the orte_job_t created by the daemon - this fixes a segfault in register_nspace on newly created daemons

* ensure orterun doesn't propagate any ess or pmix directives in its environment

* Cleanup a few valgrind issues and memory leaks

* Fix a race condition that prevented the client from completing notification registrations (missing thread shift)

* Ensure the shizo/alps component detects launch by mpirun
2016-03-01 06:53:00 -08:00

146 строки
5.1 KiB
C

/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
/*
* 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) 2015 Los Alamos National Security, LLC. All rights
* reserved.
* Copyright (c) 2016 Intel, Inc. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
*
* $HEADER$
*
* These symbols are in a file by themselves to provide nice linker
* semantics. Since linkers generally pull in symbols by object
* files, keeping these symbols as the only symbols in this file
* prevents utility programs such as "ompi_info" from having to import
* entire components just to query their version and parameters.
*/
#include "orte_config.h"
#include "orte/constants.h"
#include "opal/mca/pmix/pmix.h"
#include "opal/mca/pmix/base/base.h"
#include "orte/util/proc_info.h"
#include "orte/mca/schizo/schizo.h"
#include "orte/mca/ess/ess.h"
#include "orte/mca/ess/singleton/ess_singleton.h"
extern orte_ess_base_module_t orte_ess_singleton_module;
static int component_open(void);
static int component_close(void);
static int component_query(mca_base_module_t **module, int *priority);
static int component_register(void);
/*
* Instantiate the public struct with all of our public information
* and pointers to our public functions in it
*/
orte_ess_singleton_component_t mca_ess_singleton_component = {
{
/* First, the mca_component_t struct containing meta information
about the component itself */
.base_version = {
ORTE_ESS_BASE_VERSION_3_0_0,
/* Component name and version */
.mca_component_name = "singleton",
MCA_BASE_MAKE_VERSION(component, ORTE_MAJOR_VERSION, ORTE_MINOR_VERSION,
ORTE_RELEASE_VERSION),
/* Component open and close functions */
.mca_open_component = component_open,
.mca_close_component = component_close,
.mca_query_component = component_query,
.mca_register_component_params = component_register,
},
.base_data = {
/* The component is not checkpoint ready */
MCA_BASE_METADATA_PARAM_NONE
},
},
.server_uri = NULL,
.isolated = false
};
static int component_register(void)
{
int ret;
mca_ess_singleton_component.server_uri = NULL;
ret = mca_base_component_var_register(&mca_ess_singleton_component.super.base_version,
"server",
"Server to be used as HNP - [file|FILE]:<filename> or just uri",
MCA_BASE_VAR_TYPE_STRING, NULL, 0, 0,
OPAL_INFO_LVL_9,
MCA_BASE_VAR_SCOPE_READONLY,
&mca_ess_singleton_component.server_uri);
(void) mca_base_var_register_synonym(ret, "orte", "orte", NULL, "server", 0);
ret = mca_base_component_var_register(&mca_ess_singleton_component.super.base_version,
"isolated",
"Do not start a supporting daemon as this process will never attempt to spawn",
MCA_BASE_VAR_TYPE_BOOL, NULL, 0, 0,
OPAL_INFO_LVL_9,
MCA_BASE_VAR_SCOPE_READONLY,
&mca_ess_singleton_component.isolated);
return ORTE_SUCCESS;
}
static int component_open(void)
{
return ORTE_SUCCESS;
}
static int component_query(mca_base_module_t **module, int *priority)
{
orte_schizo_launch_environ_t ret;
/* if we are an HNP, daemon, or tool, then we
* are definitely not a singleton!
*/
if (ORTE_PROC_IS_HNP ||
ORTE_PROC_IS_DAEMON ||
ORTE_PROC_IS_TOOL) {
*module = NULL;
*priority = 0;
return ORTE_ERROR;
}
/* find out what our environment looks like */
ret = orte_schizo.check_launch_environment();
if (ORTE_SCHIZO_UNMANAGED_SINGLETON != ret &&
ORTE_SCHIZO_MANAGED_SINGLETON != ret) {
/* not us */
*module = NULL;
*priority = 0;
return ORTE_ERROR;
}
/* okay, we want to be selected as we must be a singleton */
*priority = 100;
*module = (mca_base_module_t *)&orte_ess_singleton_module;
return ORTE_SUCCESS;
}
static int component_close(void)
{
return ORTE_SUCCESS;
}