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
143 строки
5.0 KiB
C
143 строки
5.0 KiB
C
/*
|
|
* Copyright (c) 2004-2007 The Trustees of Indiana University and Indiana
|
|
* University Research and Technology
|
|
* Corporation. All rights reserved.
|
|
* Copyright (c) 2004-2006 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) 2016 Intel, Inc. All rights reserved.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/** @file:
|
|
*/
|
|
|
|
#ifndef MCA_ODLS_PRIVATE_H
|
|
#define MCA_ODLS_PRIVATE_H
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
#include "orte/types.h"
|
|
|
|
#include "opal/class/opal_list.h"
|
|
#include "opal/class/opal_pointer_array.h"
|
|
#include "opal/class/opal_bitmap.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
|
|
|
|
/*
|
|
* General ODLS types
|
|
*/
|
|
|
|
typedef struct {
|
|
/** Verbose/debug output stream */
|
|
int output;
|
|
/** Time to allow process to forcibly die */
|
|
int timeout_before_sigkill;
|
|
/* list of ranks to be displayed on separate xterms */
|
|
opal_list_t xterm_ranks;
|
|
/* the xterm cmd to be used */
|
|
char **xtermcmd;
|
|
} orte_odls_globals_t;
|
|
|
|
ORTE_DECLSPEC extern orte_odls_globals_t orte_odls_globals;
|
|
|
|
|
|
/*
|
|
* Default functions that are common to most environments - can
|
|
* be overridden by specific environments if they need something
|
|
* different (e.g., bproc)
|
|
*/
|
|
ORTE_DECLSPEC int
|
|
orte_odls_base_default_get_add_procs_data(opal_buffer_t *data,
|
|
orte_jobid_t job);
|
|
|
|
ORTE_DECLSPEC int
|
|
orte_odls_base_default_construct_child_list(opal_buffer_t *data,
|
|
orte_jobid_t *job);
|
|
|
|
/* define a function that will fork a local proc */
|
|
typedef int (*orte_odls_base_fork_local_proc_fn_t)(orte_app_context_t *context,
|
|
orte_proc_t *child,
|
|
char **environ_copy,
|
|
orte_job_t *jdata);
|
|
|
|
/* define an object for starting local launch */
|
|
typedef struct {
|
|
opal_object_t object;
|
|
opal_event_t *ev;
|
|
orte_jobid_t job;
|
|
orte_odls_base_fork_local_proc_fn_t fork_local;
|
|
int retries;
|
|
} orte_odls_launch_local_t;
|
|
OBJ_CLASS_DECLARATION(orte_odls_launch_local_t);
|
|
|
|
#define ORTE_ACTIVATE_LOCAL_LAUNCH(j, f) \
|
|
do { \
|
|
orte_odls_launch_local_t *ll; \
|
|
ll = OBJ_NEW(orte_odls_launch_local_t); \
|
|
ll->job = (j); \
|
|
ll->fork_local = (f); \
|
|
opal_event_set(orte_event_base, ll->ev, -1, OPAL_EV_WRITE, \
|
|
orte_odls_base_default_launch_local, ll); \
|
|
opal_event_set_priority(ll->ev, ORTE_SYS_PRI); \
|
|
opal_event_active(ll->ev, OPAL_EV_WRITE, 1); \
|
|
} while(0);
|
|
|
|
ORTE_DECLSPEC void orte_odls_base_default_launch_local(int fd, short sd, void *cbdata);
|
|
|
|
ORTE_DECLSPEC void odls_base_default_wait_local_proc(orte_proc_t *proc, void* cbdata);
|
|
|
|
/* define a function type to signal a local proc */
|
|
typedef int (*orte_odls_base_signal_local_fn_t)(pid_t pid, int signum);
|
|
|
|
ORTE_DECLSPEC int
|
|
orte_odls_base_default_signal_local_procs(const orte_process_name_t *proc, int32_t signal,
|
|
orte_odls_base_signal_local_fn_t signal_local);
|
|
|
|
/* define a function type for killing a local proc */
|
|
typedef int (*orte_odls_base_kill_local_fn_t)(pid_t pid, int signum);
|
|
|
|
/* define a function type to detect that a child died */
|
|
typedef bool (*orte_odls_base_child_died_fn_t)(orte_proc_t *child);
|
|
|
|
ORTE_DECLSPEC int
|
|
orte_odls_base_default_kill_local_procs(opal_pointer_array_t *procs,
|
|
orte_odls_base_kill_local_fn_t kill_local,
|
|
orte_odls_base_child_died_fn_t child_died);
|
|
|
|
ORTE_DECLSPEC int orte_odls_base_default_restart_proc(orte_proc_t *child,
|
|
orte_odls_base_fork_local_proc_fn_t fork_local);
|
|
|
|
/*
|
|
* Preload binary/files functions
|
|
*/
|
|
ORTE_DECLSPEC int orte_odls_base_preload_files_app_context(orte_app_context_t* context);
|
|
|
|
/*
|
|
* Obtain process stats on a child proc
|
|
*/
|
|
ORTE_DECLSPEC int orte_odls_base_get_proc_stats(opal_buffer_t *answer, orte_process_name_t *proc);
|
|
|
|
END_C_DECLS
|
|
|
|
#endif
|