ee5a626d25
1. Changed the RMGR and PLS APIs to add "signal_job" and "signal_proc" entry points. Only the "signal_job" entries are implemented - none of the components have implementations for "signal_proc" at this time. Thus, you can signal all of the procs in a job, but cannot currently signal only one specific proc. 2. Implemented those new API functions in all components except xgrid (Brian will do so very soon). Only the rsh/ssh and fork modules have been tested, however, and only under OS-X. 3. Added signal traps and callback functions for SIGUSR1/2 to orterun/mpirun that catch those signals and call the appropriate commands to propagate them out to all processes in the job. 4. Added a new test directory under the orte branch to (eventually) hold unit and system level tests for just the run-time. Since our test branch of the repository is under restricted access, people working on the RTE were continually developing their own system-level tests - thus making it hard to help diagnose problems. I have moved the more commonly-used functions here, and added one specifically for testing the SIGUSR1/2 functionality. I will be contacting people directly to seek help with testing the changes on more environments. Other than compile issues, you should see absolutely no change in behavior on any of your systems - this additional functionality is transparent to anyone who does not issue a SIGUSR1/2 to mpirun. Ralph This commit was SVN r10258.
86 строки
2.3 KiB
C
86 строки
2.3 KiB
C
/*
|
|
* Copyright (c) 2004-2005 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.
|
|
* $COPYRIGHT$
|
|
*
|
|
* Additional copyrights may follow
|
|
*
|
|
* $HEADER$
|
|
*/
|
|
/**
|
|
* @file:
|
|
* Part of the rsh launcher. See pls_rsh.h for an overview of how it works.
|
|
*/
|
|
|
|
#ifndef ORTE_PLS_RSH_EXPORT_H
|
|
#define ORTE_PLS_RSH_EXPORT_H
|
|
|
|
#include "orte_config.h"
|
|
|
|
#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_rsh_component_open(void);
|
|
int orte_pls_rsh_component_close(void);
|
|
orte_pls_base_module_t* orte_pls_rsh_component_init(int *priority);
|
|
|
|
/*
|
|
* Startup / Shutdown
|
|
*/
|
|
int orte_pls_rsh_finalize(void);
|
|
|
|
/*
|
|
* Interface
|
|
*/
|
|
int orte_pls_rsh_launch(orte_jobid_t);
|
|
int orte_pls_rsh_terminate_job(orte_jobid_t);
|
|
int orte_pls_rsh_terminate_proc(const orte_process_name_t* proc_name);
|
|
int orte_pls_rsh_signal_job(orte_jobid_t, int32_t);
|
|
int orte_pls_rsh_signal_proc(const orte_process_name_t* proc_name, int32_t);
|
|
|
|
/**
|
|
* PLS Component
|
|
*/
|
|
struct orte_pls_rsh_component_t {
|
|
orte_pls_base_component_t super;
|
|
bool debug;
|
|
bool reap;
|
|
bool assume_same_shell;
|
|
int delay;
|
|
int priority;
|
|
char *agent_param;
|
|
char** agent_argv;
|
|
int agent_argc;
|
|
char* agent_path;
|
|
char* orted;
|
|
size_t num_children;
|
|
size_t num_concurrent;
|
|
opal_mutex_t lock;
|
|
opal_condition_t cond;
|
|
};
|
|
typedef struct orte_pls_rsh_component_t orte_pls_rsh_component_t;
|
|
|
|
ORTE_DECLSPEC extern orte_pls_rsh_component_t mca_pls_rsh_component;
|
|
ORTE_DECLSPEC extern orte_pls_base_module_t orte_pls_rsh_module;
|
|
|
|
#if defined(c_plusplus) || defined(__cplusplus)
|
|
}
|
|
#endif
|
|
#endif /* ORTE_PLS_RSH_EXPORT_H */
|