orte_init_stage1.c

MPI stands for the Message Passing Interface. Written by the MPI Forum (a large committee comprising

/*
 * 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 (c) 2006      Los Alamos National Security, LLC.  All rights
 *                         reserved. 
 * Copyright (c) 2007      Cisco Systems, Inc.  All rights reserved.
 *
 * $COPYRIGHT$
 *
 * Additional copyrights may follow
 *
 * $HEADER$
 */

/** @file **/

#include "orte_config.h"

#include <sys/types.h>
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif

#include "orte/orte_constants.h"

#include "opal/event/event.h"
#include "opal/util/output.h"
#include "opal/util/show_help.h"
#include "opal/threads/mutex.h"
#include "opal/runtime/opal.h"
#include "opal/mca/mca.h"
#include "opal/mca/base/base.h"
#include "opal/mca/base/mca_base_param.h"
#include "opal/util/os_path.h"
#include "opal/util/cmd_line.h"
#include "opal/util/malloc.h"

#include "orte/dss/dss.h"
#include "orte/mca/rml/base/base.h"
#include "orte/mca/errmgr/base/base.h"
#include "orte/mca/iof/base/base.h"
#include "orte/mca/ns/base/base.h"
#include "orte/mca/sds/base/base.h"
#include "orte/mca/gpr/base/base.h"
#include "orte/mca/ras/base/base.h"
#include "orte/mca/rds/base/base.h"
#include "orte/mca/pls/base/base.h"
#include "orte/mca/rmgr/base/base.h"
#include "orte/mca/odls/base/base.h"

#include "orte/mca/rmaps/base/base.h"
#include "orte/mca/schema/base/base.h"
#include "orte/mca/smr/base/base.h"
#include "orte/util/univ_info.h"
#include "orte/util/proc_info.h"
#include "orte/util/session_dir.h"
#include "orte/util/sys_info.h"
#include "orte/util/universe_setup_file_io.h"

/* these are to be cleaned up for 2.0 */
#include "orte/mca/ras/base/ras_private.h"
#include "orte/mca/rmgr/base/rmgr_private.h"

#include "orte/runtime/runtime.h"
#include "orte/runtime/runtime_internal.h"
#include "orte/runtime/orte_wait.h"
#include "orte/runtime/params.h"

int orte_init_stage1(bool infrastructure)
{
    int ret;
    char *error = NULL;
    char *jobid_str = NULL;
    char *procid_str = NULL;
    char *contact_path = NULL;
    orte_jobid_t my_jobid;
    orte_cellid_t my_cellid;

    if (orte_initialized) {
        return ORTE_SUCCESS;
    }

    /* register handler for errnum -> string conversion */
    opal_error_register("ORTE", ORTE_ERR_BASE, ORTE_ERR_MAX, orte_err2str);

    /* Register all MCA Params */
    if (ORTE_SUCCESS != (ret = orte_register_params(infrastructure))) {
        error = "orte_register_params";
        goto error;
    }

    /* Ensure the system_info structure is instantiated and initialized */
    if (ORTE_SUCCESS != (ret = orte_sys_info())) {
        error = "orte_sys_info";
        goto error;
    }

    /* Ensure the process info structure is instantiated and initialized */
    if (ORTE_SUCCESS != (ret = orte_proc_info())) {
        error = "orte_proc_info";
        goto error;
    }

    /* Ensure the universe_info structure is instantiated and initialized */
    if (ORTE_SUCCESS != (ret = orte_univ_info())) {
        error = "orte_univ_info";
        goto error;
    }

    /*
     * Initialize the data storage service.
     */
    if (ORTE_SUCCESS != (ret = orte_dss_open())) {
        error = "orte_dss_open";
        goto error;
    }

    /*
     * Open the name services to ensure access to local functions
     */
    if (ORTE_SUCCESS != (ret = orte_ns_base_open())) {
        error = "orte_ns_base_open";
        goto error;
    }

    /* Open the error manager to activate error logging - needs local name services */
    if (ORTE_SUCCESS != (ret = orte_errmgr_base_open())) {
        error = "orte_errmgr_base_open";
        goto error;
    }

    /*****   ERROR LOGGING NOW AVAILABLE *****/

    /*
     * Initialize the event library
    */
    if (ORTE_SUCCESS != (ret = opal_event_init())) {
        ORTE_ERROR_LOG(ret);
        error = "opal_event_init";
        goto error;
    }

    /*
     * Intialize the general progress engine
     */
    if (ORTE_SUCCESS != (ret = opal_progress_init())) {
        ORTE_ERROR_LOG(ret);
        error = "opal_progress_init";
        goto error;
    }

    /*
     * Internal startup
     */
    if (ORTE_SUCCESS != (ret = orte_wait_init())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_wait_init";
        goto error;
    }

    /*
     * Runtime Messaging Layer
     */
    if (ORTE_SUCCESS != (ret = orte_rml_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rml_base_open";
        goto error;
    }

    /*
     * Runtime Messaging Layer
     */
    if (ORTE_SUCCESS != (ret = orte_rml_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rml_base_select";
        goto error;
    }

    /*
     * Registry
     */
    if (ORTE_SUCCESS != (ret = orte_gpr_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_gpr_base_open";
        goto error;
    }

    /*
     * Initialize schema utilities
     */
    if (ORTE_SUCCESS != (ret = orte_schema_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_schema_base_open";
        goto error;
    }

    /*
     * Initialize and select the Startup Discovery Service
     */
    if (ORTE_SUCCESS != (ret = orte_sds_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_sds_base_open";
        goto error;
    }
    if (ORTE_SUCCESS != (ret = orte_sds_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_sds_base_select";
        goto error;
    }

    /* Try to connect to the universe */
    if (ORTE_SUCCESS != (ret = orte_sds_base_contact_universe())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_sds_base_contact_universe";
        goto error;
    }

    /*
     * Name Server
     */
    if (ORTE_SUCCESS != (ret = orte_ns_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_ns_base_select";
        goto error;
    }

    /*
     * Registry
     */
    if (ORTE_SUCCESS != (ret = orte_gpr_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_gpr_base_select";
        goto error;
    }

    /* set contact info for ns/gpr */
    if(NULL != orte_process_info.ns_replica_uri) {
        orte_rml.set_uri(orte_process_info.ns_replica_uri);
    }
    if(NULL != orte_process_info.gpr_replica_uri) {
        orte_rml.set_uri(orte_process_info.gpr_replica_uri);
    }

    /* set my name and the names of the procs I was started with */
    if (ORTE_SUCCESS != (ret = orte_sds_base_set_name())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_sds_base_set_name";
        goto error;
    }

    /* all done with sds - clean up and call it a day */
    orte_sds_base_close();

    /*
     * Now that we know for certain if we are an HNP and/or a daemon,
     * setup the resource management frameworks. This includes opening
     * and selecting the daemon launch framework - that framework "knows"
     * what to do if it isn't in a daemon, and everyone needs that framework
     * to at least register its datatypes.
     */
    if (ORTE_SUCCESS != (ret = orte_rds_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rds_base_open";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_rds_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rds_base_select";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_ras_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_ras_base_open";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_ras_base_find_available())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_ras_base_find_available";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_rmaps_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rmaps_base_open";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_rmaps_base_find_available())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rmaps_base_find_available";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_pls_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_pls_base_open";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_pls_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_pls_base_select";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_odls_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_odls_base_open";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_odls_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_odls_base_select";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_rmgr_base_open())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rmgr_base_open";
        goto error;
    }
    
    if (ORTE_SUCCESS != (ret = orte_rmgr_base_select())) {
        ORTE_ERROR_LOG(ret);
        error = "orte_rmgr_base_select";
        goto error;
    }
    
    /*