06c3dfc052
* Clean up the DVM so it continues to run even when applications error out and we would ordinarily abort the daemons. * Create a new errmgr component for the DVM to handle the differences. * Cleanup the DVM state component. * Add ORTE bindings directory and brief README * Pass a local tool index around to match jobs. * Pass the jobid on job completion. * Fix initialization logic. * Add framework for python wrapper. * Fix terminate-with-non-zero-exit behavior so it properly terminates only the indicated procs, notifies orte-submit, and orte-dvm continues executing. * Add some missing options to orte-dvm * Fix a bug in -host processing that caused us to ignore the #slots designator. Add a new attribute to indicate "do not expand the DVM" when submitting job spawn requests. * It actually makes no sense that we treat the termination of all children differently than terminating the children of a specific job - it only creates confusion over the difference in behavior. So terminate children the same way regardless. Extend the cmd_line utility to easily allow layering of command line definitions Catch up with ORTE interface change and make build more generic. Disable "fixed dvm" logic for now. Add another cmd_line function to merge a table of cmd line options with another one, reporting as errors any duplicate entries. Use this to allow orterun to reuse the orted_submit code Fix the "fixed_dvm" logic by ensuring we reset num_new_daemons to zero. Also ensure that the nidmap is sent with the first job so the downstream daemons get the node info. Remove a duplicate cmd line entry in orterun. Revise the DVM startup procedure to pass the nidmap only once, at the startup of the DVM. This reduces the overhead on each job launch and ensures that the nidmap doesn't get overwritten. Add new commands to get_orted_comm_cmd_str(). Move ORTE command line options to orte_globals.[ch]. Catch up with extra orte_submit_init parameter. Add example code. Add documentation. Bump version. The nidmap and routing data must be updated prior to propagating the xcast or else the xcast will fail. Fix the return code so it is something more expected when an error occurs. Ensure we get an error returned to us when we fail to launch for some reason. In this case, we will always get a launch_cb as we did indeed attempt to spawn it. The error code will be returned in the complete_cb. Fix the return code from orte_submit_job - it was returning the tracker index instead of "success". Take advantage of ORTE's pretty-print capabilities to provide a nice error output explaining why we failed to launch. Ensure we always get a launch_cb when we fail to launch, but no complete_cb as the job never launched. Extend the error reporting capability to job completion as well. Add index parameter to orte_submit_job(). Add orte_job_cancel and implement ORTE_DAEMON_TERMINATE_JOB_CMD. Factor out dvm termination. Parse the terminate option at tool level. Add error string for ORTE_ERR_JOB_CANCELLED. Add some safeguards. Cleanup and/of comments. Enable the return. Properly ORTE_DECLSPEC orte_submit_halt. Add orte_submit_halt and orte_submit_cancel to interface. Use the plm interface to terminate the job
127 строки
4.1 KiB
C
127 строки
4.1 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) 2011-2015 Los Alamos National Security, LLC. All rights
|
|
* reserved.
|
|
* Copyright (c) 2016 Intel, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/**
|
|
* @file
|
|
*
|
|
* The OpenRTE Daemon's Local Launch Subsystem
|
|
*
|
|
*/
|
|
|
|
#ifndef ORTE_MCA_ODLS_H
|
|
#define ORTE_MCA_ODLS_H
|
|
|
|
#include "orte_config.h"
|
|
#include "orte/types.h"
|
|
|
|
#include "orte/mca/mca.h"
|
|
#include "opal/class/opal_pointer_array.h"
|
|
|
|
#include "opal/dss/dss_types.h"
|
|
#include "orte/mca/rml/rml_types.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
#include "orte/mca/odls/odls_types.h"
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/*
|
|
* odls module functions
|
|
*/
|
|
|
|
/*
|
|
* Construct a buffer for use in adding local processes
|
|
* In order to reuse daemons, we need a way for the HNP to construct a buffer that
|
|
* contains the data needed by the active ODLS component to launch a local process. Since the
|
|
* only one that knows what a particular ODLS component needs is that component, we require an
|
|
* entry point that the HNP can call to get the required buffer. This is constructed
|
|
* for *all* nodes - the individual orteds then parse that data to find the specific launch info
|
|
* for procs on their node
|
|
*/
|
|
typedef int (*orte_odls_base_module_get_add_procs_data_fn_t)(opal_buffer_t *data,
|
|
orte_jobid_t job);
|
|
|
|
/**
|
|
* Locally launch the provided processes
|
|
*/
|
|
typedef int (*orte_odls_base_module_launch_local_processes_fn_t)(opal_buffer_t *data);
|
|
|
|
/**
|
|
* Kill the local processes on this node
|
|
*/
|
|
typedef int (*orte_odls_base_module_kill_local_processes_fn_t)(opal_pointer_array_t *procs);
|
|
|
|
/**
|
|
* Signal local processes
|
|
*/
|
|
typedef int (*orte_odls_base_module_signal_local_process_fn_t)(const orte_process_name_t *proc,
|
|
int32_t signal);
|
|
|
|
/**
|
|
* Restart a local process
|
|
*/
|
|
typedef int (*orte_odls_base_module_restart_proc_fn_t)(orte_proc_t *child);
|
|
|
|
/**
|
|
* pls module version
|
|
*/
|
|
struct orte_odls_base_module_1_3_0_t {
|
|
orte_odls_base_module_get_add_procs_data_fn_t get_add_procs_data;
|
|
orte_odls_base_module_launch_local_processes_fn_t launch_local_procs;
|
|
orte_odls_base_module_kill_local_processes_fn_t kill_local_procs;
|
|
orte_odls_base_module_signal_local_process_fn_t signal_local_procs;
|
|
orte_odls_base_module_restart_proc_fn_t restart_proc;
|
|
};
|
|
|
|
/** shorten orte_odls_base_module_1_3_0_t declaration */
|
|
typedef struct orte_odls_base_module_1_3_0_t orte_odls_base_module_1_3_0_t;
|
|
/** shorten orte_odls_base_module_t declaration */
|
|
typedef struct orte_odls_base_module_1_3_0_t orte_odls_base_module_t;
|
|
|
|
/**
|
|
* odls component
|
|
*/
|
|
struct orte_odls_base_component_2_0_0_t {
|
|
/** component version */
|
|
mca_base_component_t version;
|
|
/** component data */
|
|
mca_base_component_data_t base_data;
|
|
};
|
|
/** Convenience typedef */
|
|
typedef struct orte_odls_base_component_2_0_0_t orte_odls_base_component_2_0_0_t;
|
|
/** Convenience typedef */
|
|
typedef orte_odls_base_component_2_0_0_t orte_odls_base_component_t;
|
|
|
|
|
|
/**
|
|
* Macro for use in modules that are of type odls
|
|
*/
|
|
#define ORTE_ODLS_BASE_VERSION_2_0_0 \
|
|
ORTE_MCA_BASE_VERSION_2_1_0("odls", 2, 0, 0)
|
|
|
|
/* Global structure for accessing ODLS functions
|
|
*/
|
|
ORTE_DECLSPEC extern orte_odls_base_module_t orte_odls; /* holds selected module's function pointers */
|
|
|
|
END_C_DECLS
|
|
|
|
#endif /* MCA_ODLS_H */
|