f11931306a
Correct an error wrt how jobids were being computed. Needed to ensure that the job family field was not overrun as we increment jobids for comm_spawn. Update the slurm plm module so it uses the new slurm termination procedure (brings trunk back into alignment with 1.3 branch). Update the slurmd ess component so it doesn't get selected if we are running a singleton inside of a slurm allocation. Cleanup HNP init by moving some code that had been in orte_globals.c for historical reasons into the ess hnp module, and removing the call to that code from the ess_base_std_prolog NOTE: this change allows orte to support an infinite aggregate number of comm_spawn's, with up to 64k being alive at any one instant. HOWEVER, the MPI layer currently does -not- support re-use of jobids. I did some prototype coding to revise the ompi_proc_t structures, but the BTLs are caching their own data, and there was no readily apparent way to update it. Thus, attempts to spawn more than the 64k limit will abort to avoid causing the MPI layer to hang. This commit was SVN r20700.
141 строка
4.2 KiB
C
141 строка
4.2 KiB
C
/*
|
|
* Copyright (c) 2004-2006 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:
|
|
*/
|
|
|
|
#ifndef MCA_PLM_PRIVATE_H
|
|
#define MCA_PLM_PRIVATE_H
|
|
|
|
/*
|
|
* includes
|
|
*/
|
|
#include "orte_config.h"
|
|
#include "orte/types.h"
|
|
|
|
#ifdef HAVE_SYS_TIME_H
|
|
#include <sys/time.h>
|
|
#endif /* HAVE_SYS_TIME_H */
|
|
|
|
#include "opal/class/opal_list.h"
|
|
#include "opal/threads/condition.h"
|
|
|
|
#include "opal/dss/dss_types.h"
|
|
#include "orte/mca/plm/plm_types.h"
|
|
#include "orte/mca/rml/rml_types.h"
|
|
#include "orte/mca/odls/odls_types.h"
|
|
#include "orte/runtime/orte_globals.h"
|
|
|
|
|
|
BEGIN_C_DECLS
|
|
|
|
/* globals for use solely within PLM framework */
|
|
typedef struct {
|
|
/** Verbose/debug output stream */
|
|
int output;
|
|
/* orted cmd comm lock */
|
|
opal_mutex_t orted_cmd_lock;
|
|
/* orted cmd cond */
|
|
opal_condition_t orted_cmd_cond;
|
|
/* next jobid */
|
|
uint16_t next_jobid;
|
|
/* time when daemons started launch */
|
|
struct timeval daemonlaunchstart;
|
|
/* rsh launch agent path */
|
|
char *rsh_agent_path;
|
|
/* rsh launch agent argv */
|
|
char **rsh_agent_argv;
|
|
/* jobid for local slaves */
|
|
orte_jobid_t local_slaves;
|
|
} orte_plm_globals_t;
|
|
/**
|
|
* Global instance of PLM framework data
|
|
*/
|
|
ORTE_DECLSPEC extern orte_plm_globals_t orte_plm_globals;
|
|
|
|
|
|
/**
|
|
* Utility routine to set progress engine schedule
|
|
*/
|
|
ORTE_DECLSPEC int orte_plm_base_set_progress_sched(int sched);
|
|
|
|
/*
|
|
* Launch support
|
|
*/
|
|
ORTE_DECLSPEC int orte_plm_base_setup_job(orte_job_t *jdata);
|
|
ORTE_DECLSPEC int orte_plm_base_launch_apps(orte_jobid_t job);
|
|
ORTE_DECLSPEC void orte_plm_base_launch_failed(orte_jobid_t job, pid_t pid, int status, orte_job_state_t state);
|
|
|
|
ORTE_DECLSPEC int orte_plm_base_daemon_callback(orte_std_cntr_t num_daemons);
|
|
|
|
ORTE_DECLSPEC void orte_plm_base_check_job_completed(orte_job_t *jdata);
|
|
|
|
ORTE_DECLSPEC int orte_plm_base_set_hnp_name(void);
|
|
|
|
ORTE_DECLSPEC int orte_plm_base_create_jobid(orte_jobid_t *jobid);
|
|
|
|
ORTE_DECLSPEC int orte_plm_base_setup_orted_cmd(int *argc, char ***argv);
|
|
|
|
/**
|
|
* Local slave launch
|
|
*/
|
|
ORTE_DECLSPEC int orte_plm_base_local_slave_launch(orte_job_t *jdata);
|
|
ORTE_DECLSPEC int orte_plm_base_rsh_launch_agent_setup(void);
|
|
|
|
/**
|
|
* Heartbeat support
|
|
*/
|
|
ORTE_DECLSPEC void orte_plm_base_heartbeat(int fd, short event, void *data);
|
|
ORTE_DECLSPEC void orte_plm_base_start_heart(void);
|
|
|
|
/**
|
|
* Utilities for plm components that use proxy daemons
|
|
*/
|
|
ORTE_DECLSPEC int orte_plm_base_orted_exit(orte_daemon_cmd_flag_t command);
|
|
ORTE_DECLSPEC int orte_plm_base_orted_kill_local_procs(orte_jobid_t job);
|
|
ORTE_DECLSPEC int orte_plm_base_orted_signal_local_procs(orte_jobid_t job, int32_t signal);
|
|
|
|
/*
|
|
* communications utilities
|
|
*/
|
|
ORTE_DECLSPEC int orte_plm_base_comm_start(void);
|
|
ORTE_DECLSPEC int orte_plm_base_comm_stop(void);
|
|
ORTE_DECLSPEC void orte_plm_base_recv(int status, orte_process_name_t* sender,
|
|
opal_buffer_t* buffer, orte_rml_tag_t tag,
|
|
void* cbdata);
|
|
|
|
|
|
/**
|
|
* Construct basic ORTE Daemon command line arguments
|
|
*/
|
|
ORTE_DECLSPEC int orte_plm_base_orted_append_basic_args(int *argc, char ***argv,
|
|
char *sds,
|
|
int *proc_vpid_index,
|
|
bool heartbeat);
|
|
|
|
/*
|
|
* Proxy functions for use by daemons and application procs
|
|
* needing dynamic operations
|
|
*/
|
|
ORTE_DECLSPEC int orte_plm_proxy_init(void);
|
|
ORTE_DECLSPEC int orte_plm_proxy_spawn(orte_job_t *jdata);
|
|
ORTE_DECLSPEC int orte_plm_proxy_finalize(void);
|
|
|
|
END_C_DECLS
|
|
|
|
#endif /* MCA_PLS_PRIVATE_H */
|