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
103 строки
2.8 KiB
C
103 строки
2.8 KiB
C
/* -*- Mode: C; c-basic-offset:4 ; indent-tabs-mode:nil -*- */
|
|
/*
|
|
* Copyright (c) 2010 Cisco Systems, Inc. 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
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
|
|
#include "orte_config.h"
|
|
#include "opal/util/output.h"
|
|
|
|
#include "orte/mca/errmgr/errmgr.h"
|
|
#include "orte/mca/errmgr/base/base.h"
|
|
#include "orte/mca/errmgr/base/errmgr_private.h"
|
|
#include "errmgr_dvm.h"
|
|
|
|
/*
|
|
* Public string for version number
|
|
*/
|
|
const char *orte_errmgr_dvm_component_version_string =
|
|
"ORTE ERRMGR dvm MCA component version " ORTE_VERSION;
|
|
|
|
/*
|
|
* Local functionality
|
|
*/
|
|
static int dvm_register(void);
|
|
static int dvm_open(void);
|
|
static int dvm_close(void);
|
|
static int dvm_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_errmgr_base_component_t mca_errmgr_dvm_component = {
|
|
/* Handle the general mca_component_t struct containing
|
|
* meta information about the component dvm
|
|
*/
|
|
.base_version = {
|
|
ORTE_ERRMGR_BASE_VERSION_3_0_0,
|
|
/* Component name and version */
|
|
.mca_component_name = "dvm",
|
|
MCA_BASE_MAKE_VERSION(component, ORTE_MAJOR_VERSION, ORTE_MINOR_VERSION,
|
|
ORTE_RELEASE_VERSION),
|
|
|
|
/* Component open and close functions */
|
|
.mca_open_component = dvm_open,
|
|
.mca_close_component = dvm_close,
|
|
.mca_query_component = dvm_component_query,
|
|
.mca_register_component_params = dvm_register,
|
|
},
|
|
.base_data = {
|
|
/* The component is checkpoint ready */
|
|
MCA_BASE_METADATA_PARAM_CHECKPOINT
|
|
},
|
|
};
|
|
|
|
static int my_priority;
|
|
|
|
static int dvm_register(void)
|
|
{
|
|
mca_base_component_t *c = &mca_errmgr_dvm_component.base_version;
|
|
|
|
my_priority = 1000;
|
|
(void) mca_base_component_var_register(c, "priority",
|
|
"Priority of the dvm errmgr component",
|
|
MCA_BASE_VAR_TYPE_INT, NULL, 0, 0,
|
|
OPAL_INFO_LVL_9,
|
|
MCA_BASE_VAR_SCOPE_READONLY, &my_priority);
|
|
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
static int dvm_open(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
static int dvm_close(void)
|
|
{
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
static int dvm_component_query(mca_base_module_t **module, int *priority)
|
|
{
|
|
/* used by DVM masters */
|
|
if (ORTE_PROC_IS_MASTER) {
|
|
*priority = my_priority;
|
|
*module = (mca_base_module_t *)&orte_errmgr_dvm_module;
|
|
return ORTE_SUCCESS;
|
|
}
|
|
|
|
*module = NULL;
|
|
*priority = -1;
|
|
return ORTE_ERROR;
|
|
}
|