85df3bd92f
1. generalize orte_rml.xcast to become a general broadcast-like messaging system. Messages can now be sent to any tag on the daemons or processes. Note that any message sent via xcast will be delivered to ALL processes in the specified job - you don't get to pick and choose. At a later date, we will introduce an augmented capability that will use the daemons as relays, but will allow you to send to a specified array of process names. 2. extended orte_rml.xcast so it supports more scalable message routing methodologies. At the moment, we support three: (a) direct, which sends the message directly to all recipients; (b) linear, which sends the message to the local daemon on each node, which then relays it to its own local procs; and (b) binomial, which sends the message via a binomial algo across all the daemons, each of which then relays to its own local procs. The crossover points between the algos are adjustable via MCA param, or you can simply demand that a specific algo be used. 3. orteds no longer exhibit two types of behavior: bootproxy or VM. Orteds now always behave like they are part of a virtual machine - they simply launch a job if mpirun tells them to do so. This is another step towards creating an "orteboot" functionality, but also provided a clean system for supporting message relaying. Note one major impact of this commit: multiple daemons on a node cannot be supported any longer! Only a single daemon/node is now allowed. This commit is known to break support for the following environments: POE, Xgrid, Xcpu, Windows. It has been tested on rsh, SLURM, and Bproc. Modifications for TM support have been made but could not be verified due to machine problems at LANL. Modifications for SGE have been made but could not be verified. The developers for the non-verified environments will be separately notified along with suggestions on how to fix the problems. This commit was SVN r15007.
96 строки
2.5 KiB
C
96 строки
2.5 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 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"
|
|
|
|
#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_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, struct timeval *timeout, opal_list_t*);
|
|
int orte_pls_rsh_terminate_orteds(struct timeval *timeout, opal_list_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, opal_list_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 debug_malloc;
|
|
bool debug_daemons;
|
|
bool timing;
|
|
bool reap;
|
|
bool assume_same_shell;
|
|
bool force_rsh;
|
|
int delay;
|
|
int priority;
|
|
char *agent_param;
|
|
char** agent_argv;
|
|
int agent_argc;
|
|
char* agent_path;
|
|
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_rsh_component_t orte_pls_rsh_component_t;
|
|
|
|
ORTE_MODULE_DECLSPEC extern orte_pls_rsh_component_t mca_pls_rsh_component;
|
|
extern orte_pls_base_module_t orte_pls_rsh_module;
|
|
|
|
#if defined(c_plusplus) || defined(__cplusplus)
|
|
}
|
|
#endif
|
|
#endif /* ORTE_PLS_RSH_EXPORT_H */
|