2006-09-14 21:29:51 +00:00
|
|
|
/*
|
|
|
|
* 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 bproc launching system. This launching system is broken into 2
|
|
|
|
* parts: one runs under the PLS on the head node to launch the orteds, and the
|
|
|
|
* other serves as the orted's local launcher.
|
|
|
|
*
|
|
|
|
* The main job of this component is to setup ptys/pipes for IO forwarding.
|
|
|
|
* See pls_bproc.h for an overview of how the entire bproc launching system works.
|
|
|
|
*/
|
|
|
|
#ifndef ORTE_ODLS_BPROC_H_
|
|
|
|
#define ORTE_ODLS_BPROC_H_
|
|
|
|
|
|
|
|
#include "orte_config.h"
|
|
|
|
|
|
|
|
#include <sys/bproc.h>
|
|
|
|
|
|
|
|
#include "opal/mca/mca.h"
|
|
|
|
#include "opal/threads/condition.h"
|
|
|
|
|
2006-11-17 19:06:10 +00:00
|
|
|
#include "orte/mca/gpr/gpr_types.h"
|
|
|
|
#include "orte/mca/rmaps/rmaps_types.h"
|
|
|
|
|
2006-09-14 21:29:51 +00:00
|
|
|
#include "orte/mca/odls/odls.h"
|
|
|
|
|
|
|
|
#if defined(c_plusplus) || defined(__cplusplus)
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Module open / close
|
|
|
|
*/
|
|
|
|
int orte_odls_bproc_component_open(void);
|
|
|
|
int orte_odls_bproc_component_close(void);
|
|
|
|
int orte_odls_bproc_finalize(void);
|
|
|
|
orte_odls_base_module_t* orte_odls_bproc_init(int *priority);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Startup / Shutdown
|
|
|
|
*/
|
|
|
|
int orte_odls_bproc_finalize(void);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Interface
|
|
|
|
*/
|
2006-11-17 19:06:10 +00:00
|
|
|
int orte_odls_bproc_get_add_procs_data(orte_gpr_notify_data_t **data, orte_job_map_t *map);
|
2007-07-13 15:47:57 +00:00
|
|
|
int orte_odls_bproc_launch_local_procs(orte_gpr_notify_data_t *data);
|
2006-09-14 21:29:51 +00:00
|
|
|
int orte_odls_bproc_kill_local_procs(orte_jobid_t job, bool set_state);
|
2006-11-03 20:45:22 +00:00
|
|
|
int orte_odls_bproc_signal_local_procs(const orte_process_name_t* proc_name, int32_t signal);
|
2007-04-24 18:54:45 +00:00
|
|
|
int orte_odls_bproc_deliver_message(orte_jobid_t job, orte_buffer_t *buffer, orte_rml_tag_t tag);
|
2006-09-14 21:29:51 +00:00
|
|
|
|
|
|
|
/**
|
|
|
|
* ODLS bproc_orted component
|
|
|
|
*/
|
|
|
|
struct orte_odls_bproc_component_t {
|
|
|
|
orte_odls_base_component_t super;
|
|
|
|
/**< The base class */
|
|
|
|
int debug;
|
|
|
|
/**< If greater than 0 print debugging information */
|
|
|
|
int priority;
|
|
|
|
/**< The priority of this component. This will be returned if we determine
|
|
|
|
* that bproc is available and running on this node, */
|
|
|
|
opal_mutex_t lock;
|
|
|
|
/**< Lock used to prevent some race conditions */
|
|
|
|
opal_condition_t cond;
|
|
|
|
/**< Condition used to wake up waiting threads */
|
|
|
|
opal_list_t children;
|
|
|
|
/**< list of children on this node */
|
|
|
|
};
|
|
|
|
/**
|
|
|
|
* Convenience typedef
|
|
|
|
*/
|
|
|
|
typedef struct orte_odls_bproc_component_t orte_odls_bproc_component_t;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* List object to locally store the process names and pids of
|
|
|
|
* our children. This can subsequently be used to order termination
|
|
|
|
* or pass signals without looking the info up again.
|
|
|
|
*/
|
|
|
|
typedef struct odls_bproc_child_t {
|
|
|
|
opal_list_item_t super; /* required to place this on a list */
|
|
|
|
orte_process_name_t *name; /* the OpenRTE name of the proc */
|
|
|
|
pid_t pid; /* local pid of the proc */
|
|
|
|
orte_std_cntr_t app_idx; /* index of the app_context for this proc */
|
|
|
|
bool alive; /* is this proc alive? */
|
Bring in the generalized xcast communication system along with the correspondingly revised orted launch. I will send a message out to developers explaining the basic changes. In brief:
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.
2007-06-12 13:28:54 +00:00
|
|
|
orte_vpid_t local_rank; /* local rank of this proc */
|
|
|
|
orte_std_cntr_t num_procs; /* number of local procs sharing this node */
|
2006-09-14 21:29:51 +00:00
|
|
|
} odls_bproc_child_t;
|
2006-10-06 07:24:34 +00:00
|
|
|
OBJ_CLASS_DECLARATION(odls_bproc_child_t);
|
2006-09-14 21:29:51 +00:00
|
|
|
|
2006-10-06 07:24:34 +00:00
|
|
|
ORTE_MODULE_DECLSPEC extern orte_odls_bproc_component_t mca_odls_bproc_component;
|
|
|
|
extern orte_odls_base_module_t orte_odls_bproc_module;
|
2006-09-14 21:29:51 +00:00
|
|
|
|
|
|
|
#if defined(c_plusplus) || defined(__cplusplus)
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
#endif /* ORTE_ODLS_BPROC_H_ */
|
|
|
|
|