1
1
openmpi/orte/runtime/runtime.h

190 строки
6.6 KiB
C
Исходник Обычный вид История

/*
* 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
*
* Interface into the Open MPI Run Time Environment
*/
#ifndef ORTE_RUNTIME_H
#define ORTE_RUNTIME_H
#include "orte_config.h"
#ifdef HAVE_SYS_TYPES_H
#include <sys/types.h>
#endif
#include "orte/mca/gpr/gpr_types.h"
#include "opal/util/cmd_line.h"
2004-09-23 18:40:05 +04:00
#include "orte/runtime/runtime_types.h"
#include "orte/util/univ_info.h"
#include "orte/mca/ns/ns.h"
/* constants for spawn constraints */
/** Spawn constraint - require multi-cell support. The selected spawn
system must be capable of starting across multiple cells. This
allows multiple pcms to be used to satisfy a single resource
allocation request */
#define OMPI_RTE_SPAWN_MULTI_CELL 0x0001
/** Spawn constraint - require ability to launch daemons. The
selected spawn system must be capable of starting daemon process.
Setting this flag will result in a spawn service that does not
neccessarily provide process monitoring or standard I/O
forwarding. The calling process may exit before all children have
exited. */
#define OMPI_RTE_SPAWN_DAEMON 0x0002
/** Spawn constraint - require quality of service support. The
selected spawn system must provide I/O forwarding, quick process
shutdown, and process status monitoring. */
#define OMPI_RTE_SPAWN_HIGH_QOS 0x0004
/** Spawn constraint - caller is an MPI process. The caller is an MPI
application (has called MPI_Init). This should be used only for
MPI_COMM_SPAWN and MPI_COMM_SPAWN_MULTIPLE. The calling process
will follow the semantics of the MPI_COMM_SPAWN_* functions. */
#define OMPI_RTE_SPAWN_FROM_MPI 0x0008
/** Spawn constraint - require ability to launch either MPMD (hence
the name) applications or applications with specific placement of
processes. */
#define OMPI_RTE_SPAWN_MPMD 0x0010
#if defined(c_plusplus) || defined(__cplusplus)
extern "C" {
#endif
/* globals used by RTE - instanced in orte_init.c */
ORTE_DECLSPEC extern int orte_debug_flag;
/**
* Abort the current application
*
* Aborts currently running application, NOTE: We do NOT call the
* regular C-library "abort" function, even
* though that would have alerted us to the fact that this is
* an abnormal termination, because it would automatically cause
* a core file to be generated. The "report" flag indicates if the
* function should create an appropriate file to alert the local
* orted that termination was abnormal.
*/
ORTE_DECLSPEC int orte_abort(int status, bool report);
/**
* Initialize the Open Run Time Environment
*
* Initlize the Open Run Time Environment, including process
* control, malloc debugging and threads, and out of band messaging.
* This function should be called exactly once. This function should
* be called by every application using the RTE interface, including
* MPI applications and mpirun.
*
* @param infrastructure Whether we are ORTE infrastructure or an ORTE
* application
*/
ORTE_DECLSPEC int orte_init(bool infrastructure);
ORTE_DECLSPEC int orte_system_init(bool infrastructure);
ORTE_DECLSPEC int orte_init_stage1(bool infrastructure);
ORTE_DECLSPEC int orte_init_stage2(void);
/**
* Initialize parameters for ORTE.
*
* @retval ORTE_SUCCESS Upon success.
* @retval ORTE_ERROR Upon failure.
*/
ORTE_DECLSPEC int orte_register_params(bool infrastructure);
/**
* Re-init the Open run time environment.
*
* Restart selected components with a new process name.
*/
ORTE_DECLSPEC int orte_restart(orte_process_name_t* name, const char* uri);
/**
* Finalize the Open run time environment. Any function calling \code
* orte_init should call \code orte_finalize.
*
2004-09-23 18:40:05 +04:00
*/
ORTE_DECLSPEC int orte_finalize(void);
ORTE_DECLSPEC int orte_system_finalize(void);
/*
* Change state as processes complete registration/unregistration
*/
ORTE_DECLSPEC void orte_all_procs_registered(orte_gpr_notify_message_t* match, void* cbdata);
ORTE_DECLSPEC void orte_all_procs_unregistered(orte_gpr_notify_message_t* match, void* cbdata);
ORTE_DECLSPEC int orte_monitor_procs_registered(void);
ORTE_DECLSPEC int orte_monitor_procs_unregistered(void);
Brining over the session directory and universe changes from the tmp/jjhursey-ft-cr branch. In this commit we change the way universe names are created. Before we by default first created "default-universe" then if there was a conflict we created "default-universe-PID" where PID is the PID of the HNP. Now we create "default-universe-PID" all the time (when a default universe name is used). This makes it much easier when trying to find a HNP from an outside app (e.g. orte-ps, orteconsole, ...) This also adds a "search" function to find all of the universes on the machine. This is useful in many contexts when trying to find a persistent daemon or when trying to connect to a HNP. This commit also makes orte_universe_t an opal_object_t, which is something that needed to happen, and only effected the SDS in one of it's base functions. I was asked to bring this over to aid in fixing orteconsole and orteprobe. Due to the change of orte_universe_t to an object orteprobe may need to be updated to reflect this change. Since orteprobe needs to be looked at anyway I'll leave this to Ralph to take care of. *Note*: These changes do not depend upon any of the FT work (but the FT work does depend upon them). These were brought over to help in fixing some of the ORTE tool set that require the functionality layed out in this patch. Testing: Ran the 'ibm' tests before and after this change, and all was as well as before the change. If anyone notices additional irregularities in the system let me know. But none are expected. This commit was SVN r10550.
2006-06-29 01:03:31 +04:00
/**
* Obtain a listing of all the universes on the machine
*
* @param univ_list An opal_list_t is returned to the user.
* This is not initalized in the function, the caller retains
* the responsibility for this variable.
* @retval ORTE_SUCCESS Upon successful search.
* @retval ORTE_ERROR Upon unsuccessful search.
*/
ORTE_DECLSPEC int orte_universe_search(opal_list_t *universe_list);
Brining over the session directory and universe changes from the tmp/jjhursey-ft-cr branch. In this commit we change the way universe names are created. Before we by default first created "default-universe" then if there was a conflict we created "default-universe-PID" where PID is the PID of the HNP. Now we create "default-universe-PID" all the time (when a default universe name is used). This makes it much easier when trying to find a HNP from an outside app (e.g. orte-ps, orteconsole, ...) This also adds a "search" function to find all of the universes on the machine. This is useful in many contexts when trying to find a persistent daemon or when trying to connect to a HNP. This commit also makes orte_universe_t an opal_object_t, which is something that needed to happen, and only effected the SDS in one of it's base functions. I was asked to bring this over to aid in fixing orteconsole and orteprobe. Due to the change of orte_universe_t to an object orteprobe may need to be updated to reflect this change. Since orteprobe needs to be looked at anyway I'll leave this to Ralph to take care of. *Note*: These changes do not depend upon any of the FT work (but the FT work does depend upon them). These were brought over to help in fixing some of the ORTE tool set that require the functionality layed out in this patch. Testing: Ran the 'ibm' tests before and after this change, and all was as well as before the change. If anyone notices additional irregularities in the system let me know. But none are expected. This commit was SVN r10550.
2006-06-29 01:03:31 +04:00
/**
* Check for universe existence
*
Some of these didn't really change - I was just in/out of them for diagnostics while chasing a bug. Got caught by my good buddy Tim again :) on his parse_contact_info function, which requires that the space for the answer be allocated in advance. Sigh. Anyway, mpirun2 now works again. My apologies if you tried it in the last few hours and found it didn't. Also removed the mpirun3 directory since we are basically dragging mpirun2 along with us - no need to create a new version after all. Made a few changes to the universe info structure, eliminating the "webserver" and "socket" fields since we will do those contacts through the oob channel. Also changed the "silent_mode" field to "console" since silent mode is the default - the flag needs to tell you to turn the console on, not off. Parse environ function now gets the ns and gpr replica contact info and loads it in the proper places to hand it off to the respective components, thus allowing me to check connection to them as part of determining if the named universe already exists. Changed the local_universe_exists function accordingly and gave it a new name (since the replicas may not be local). This name will shortly be changed to "ompi_rte_join_universe" as I complete the logic for doing that function. Please let me know if you see any problems. I successfully ran some trivial multi-process functions in both mpirun2 and singleton modes, and ran the seed daemon as well, so I think it should all be okay. This commit was SVN r2611.
2004-09-11 16:56:52 +04:00
* Checks to see if a specified universe exists. If so, attempts
* to connect to verify that the universe is accepting connections.
Some of these didn't really change - I was just in/out of them for diagnostics while chasing a bug. Got caught by my good buddy Tim again :) on his parse_contact_info function, which requires that the space for the answer be allocated in advance. Sigh. Anyway, mpirun2 now works again. My apologies if you tried it in the last few hours and found it didn't. Also removed the mpirun3 directory since we are basically dragging mpirun2 along with us - no need to create a new version after all. Made a few changes to the universe info structure, eliminating the "webserver" and "socket" fields since we will do those contacts through the oob channel. Also changed the "silent_mode" field to "console" since silent mode is the default - the flag needs to tell you to turn the console on, not off. Parse environ function now gets the ns and gpr replica contact info and loads it in the proper places to hand it off to the respective components, thus allowing me to check connection to them as part of determining if the named universe already exists. Changed the local_universe_exists function accordingly and gave it a new name (since the replicas may not be local). This name will shortly be changed to "ompi_rte_join_universe" as I complete the logic for doing that function. Please let me know if you see any problems. I successfully ran some trivial multi-process functions in both mpirun2 and singleton modes, and ran the seed daemon as well, so I think it should all be okay. This commit was SVN r2611.
2004-09-11 16:56:52 +04:00
* If both ns and gpr replicas provided, first checks for those
* connections. Gets any missing info from the universe contact.
*
* @param univ Pointer to universe info struct where any found info
* is to be stored
*
* @retval ORTE_SUCCESS Universe found and connection accepted
* @retval OMPI_NO_CONNECTION_ALLOWED Universe found, but not persistent or
* restricted to local scope
* @retval OMPI_CONNECTION_FAILED Universe found, but connection attempt
* failed. Probably caused by unclean termination of the universe seed
* daemon.
* @retval OMPI_CONNECTION_REFUSED Universe found and contact made, but
* universe refused to allow connection.
*/
ORTE_DECLSPEC int orte_universe_exists(orte_universe_t *univ);
/**
* Setup I/O forwarding.
*/
ORTE_DECLSPEC int ompi_rte_init_io(void);
/**
* Establish a Head Node Process on a cluster's front end
*/
ORTE_DECLSPEC int orte_setup_hnp(char *target_cluster, char *headnode, char *username);
#if defined(c_plusplus) || defined(__cplusplus)
}
#endif
#endif /* OMPI_RUNTIME_H */