ab5ea61100
1. add a "cancel_operation" API to the pls components that allows orterun to demand that an orted operation (e.g., terminate_job) be immediately cancelled and abandoned. 2. changes the pls orted commands from blocking to non-blocking. This allows us to interrupt those operations should an orted be non-responsive. The change also adds an orte_abort_timeout that limits how long orterun will automatically wait for the orteds to respond - if the terminate command, for example, doesn't see orted response within that time, then we printout an appropriate error message and just give up. 3. modifies orterun to allow multiple ctrl-c's to simply abort the program even if the orteds have not responded 4. does some cleanup on the orte-level mca params so that their implementation looks a lot more like that of ompi - makes it easier to maintain. This change also includes the definition of an orte_abort_timeout struct and associated MCA param (can't have too many!) so you can set the time after which orterun gives up on waiting for orteds to respond This needs more testing before migrating to 1.2. This commit was SVN r13304.
92 строки
2.6 KiB
C
92 строки
2.6 KiB
C
/*
|
|
* Copyright (c) 2004-2005 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.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/**
|
|
* @file:
|
|
* Part of the process launcher. See pls_process.h for an overview of how it works.
|
|
*/
|
|
|
|
#ifndef ORTE_PLS_RSH_EXPORT_H
|
|
#define ORTE_PLS_RSH_EXPORT_H
|
|
|
|
#include "orte_config.h"
|
|
|
|
#ifdef HAVE_SYS_TIME_H
|
|
#include <sys/time.h>
|
|
#endif
|
|
|
|
#include "opal/threads/condition.h"
|
|
#include "opal/mca/mca.h"
|
|
#include "orte/mca/pls/pls.h"
|
|
|
|
#if defined(c_plusplus) || defined(__cplusplus)
|
|
extern "C" {
|
|
#endif
|
|
|
|
/*
|
|
* Module open / close
|
|
*/
|
|
int orte_pls_process_component_open(void);
|
|
int orte_pls_process_component_close(void);
|
|
orte_pls_base_module_t* orte_pls_process_component_init(int *priority);
|
|
|
|
/*
|
|
* Startup / Shutdown
|
|
*/
|
|
int orte_pls_process_finalize(void);
|
|
|
|
/*
|
|
* Interface
|
|
*/
|
|
int orte_pls_process_launch(orte_jobid_t);
|
|
int orte_pls_process_terminate_job(orte_jobid_t, struct timeval *timeout, opal_list_t*);
|
|
int orte_pls_process_terminate_orteds(orte_jobid_t, struct timeval *timeout, opal_list_t*);
|
|
int orte_pls_process_terminate_proc(const orte_process_name_t* proc_name);
|
|
int orte_pls_process_signal_job(orte_jobid_t, int32_t, opal_list_t*);
|
|
int orte_pls_process_signal_proc(const orte_process_name_t* proc_name, int32_t);
|
|
int orte_pls_process_cancel_operation(void);
|
|
|
|
/**
|
|
* PLS Component
|
|
*/
|
|
struct orte_pls_process_component_t {
|
|
orte_pls_base_component_t super;
|
|
bool debug;
|
|
bool debug_malloc;
|
|
bool debug_daemons;
|
|
bool timing;
|
|
bool reap;
|
|
bool assume_same_shell;
|
|
bool force_process;
|
|
int delay;
|
|
int priority;
|
|
char* orted;
|
|
orte_std_cntr_t num_children;
|
|
orte_std_cntr_t num_concurrent;
|
|
opal_mutex_t lock;
|
|
opal_condition_t cond;
|
|
};
|
|
typedef struct orte_pls_process_component_t orte_pls_process_component_t;
|
|
|
|
ORTE_MODULE_DECLSPEC extern orte_pls_process_component_t mca_pls_process_component;
|
|
extern orte_pls_base_module_t orte_pls_process_module;
|
|
|
|
#if defined(c_plusplus) || defined(__cplusplus)
|
|
}
|
|
#endif
|
|
#endif /* ORTE_PLS_RSH_EXPORT_H */
|