ras_loadleveler_module.c

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

    /* Specify that this is a QUERY_STEPID type of query. */
    rc = ll_set_request(queryObject, QUERY_STEPID, job_step_list, ALL_DATA);
    if(0 != rc) {
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: ll_set request failed: error "
                    "%d!", rc);
        return ORTE_ERROR;
    }

    /* Get a Job object from LoadL_schedd that contains the relevant job step */
    job = ll_get_objs(queryObject, LL_SCHEDD, schedd_host_name, &obj_count, 
                      &err_code);
    if(NULL == job) {
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: ll_set request failed: error "
                    "%d!", rc);
        return ORTE_ERROR;
    }

    if (obj_count != 1) {  /* Only 1 Job object is expected. */
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: ll_get_objs: expected one job " 
                    "to match, got %d!", obj_count);
        return ORTE_ERROR;
    }

    if(0 != (rc = ll_get_data(job, LL_JobStepCount, &job_step_count))) {
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: ll_get_data: failure. RC= %d!",
                    rc);
        return ORTE_ERROR;
    }
    if (job_step_count != 1) { /* Only 1 Job Step object is expected. */
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: ll_get_objs: expected one job "
                    "step to match, got %d!", obj_count);
        return ORTE_ERROR;
    }

    step = NULL;
    if(0 != (rc = ll_get_data(job, LL_JobGetFirstStep, &step))) {
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: ll_get_data: failure. RC= %d!",
                    rc);
        return ORTE_ERROR;
    }
    if(NULL == step) {
        opal_output(orte_ras_base.ras_output,
                    "ll_get_data() Error: Unable to obtain Job Step "
                    "information.\n");
        return ORTE_ERROR;
    }

    step_mode = -1;
    if(0 != (rc = ll_get_data(step, LL_StepParallelMode, &step_mode))) {
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: ll_get_data: failure on "
                    "LL_StepParallelMode. RC= %d!", rc);
        return ORTE_ERROR;
    }
    
    /* Serial job step: step_mode==0; Parallel: step_mode==1; Others:2,3,4. */
    if ((step_mode != 0) && (step_mode != 1)) {
        opal_output(orte_ras_base.ras_output,
                    "ras:loadleveler:allocate: We support only Serial and "
                    "Parallel LoadLeveler job types. PVM, NQS, and Blue Gene"
                    "jobs are not supported by the LoadLeveler RAS!");
        return ORTE_ERROR;
    }
                        
    if(step_mode == 0) { /* serial job */
        node = NULL;
        if(0 != (rc = ll_get_data(step, LL_StepGetFirstNode, &node))) {
            opal_output(orte_ras_base.ras_output,
                        "ras:loadleveler:allocate: ll_get_data: failure on "
                        "LL_StepGetFirstNode. RC= %d!", rc);
            return ORTE_ERROR;
        }
        task = NULL;
        if(0 != (rc = ll_get_data(node, LL_NodeGetFirstTask, &task))) {
            opal_output(orte_ras_base.ras_output,
                        "ras:loadleveler:allocate: ll_get_data: failure on "
                        "LL_NodeGetFirstTask. RC= %d!", rc);
            return ORTE_ERROR;
        }
        task_instance = NULL;
        rc = ll_get_data(task, LL_TaskGetFirstTaskInstance, &task_instance);
        if(0 != rc) {
            opal_output(orte_ras_base.ras_output,
                        "ras:loadleveler:allocate: ll_get_data: failure on "
                        "LL_TaskGetFirstInstance. RC= %d!", rc);
            return ORTE_ERROR;
        }
        task_machine_name = NULL;
        if(0 != (rc = ll_get_data(task_instance, LL_TaskInstanceMachineName, 
                                  &task_machine_name))) {
            opal_output(orte_ras_base.ras_output,
                        "ras:loadleveler:allocate: ll_get_data: failure on " 
                        "LL_TaskInstanceMachineName. RC= %d!", rc);
            return ORTE_ERROR;
        }
        opal_argv_append(num_hosts, hostlist, task_machine_name);

    } else { /* parallel job */

        node = NULL;
        if(0 != (rc = ll_get_data(step, LL_StepGetFirstNode, &node))) {
            opal_output(orte_ras_base.ras_output,
                        "ras:loadleveler:allocate: ll_get_data: failure on "
                        "LL_StepGetFirstNode. RC= %d!", rc);
            return ORTE_ERROR;
        }
    
        while(NULL != node) {     /* Loop through the "Node" objects. */
            task = NULL;
            if(0 != (rc = ll_get_data(node, LL_NodeGetFirstTask, &task))) {
                opal_output(orte_ras_base.ras_output,
                            "ras:loadleveler:allocate: ll_get_data: failure on "
                            "LL_NodeGetFirstTask. RC= %d!", rc);
                return ORTE_ERROR;
            }
        
            while(task) {  /* Loop through the "Task" objects. */
                ll_master_task = 0;
                rc = ll_get_data(task, LL_TaskIsMaster, &ll_master_task);
                if(0 != rc) {
                    opal_output(orte_ras_base.ras_output,
                                "ras:loadleveler:allocate: ll_get_data: failure" 
                                "  on LL_TaskIsMaster. RC= %d!", rc);
                    return ORTE_ERROR;
                }
            
                /* The "master task" Task object is a LoadLeveler abstraction 
                 * and is not relevant here. Look at only Task objects that 
                 * are not "master".*/
                if (!ll_master_task) {
                    task_instance = NULL;
                    if(0 != (rc = ll_get_data(task, LL_TaskGetFirstTaskInstance,
                                              &task_instance))) {
                        opal_output(orte_ras_base.ras_output,
                                    "ras:loadleveler:allocate: ll_get_data: "
                                    "failure on LL_TaskGetFirstTaskInstance. "
                                    " RC= %d!", rc);
                        return ORTE_ERROR;
                    }
                
                    /* Loop through the "Task Instance" objects. */
                    while (task_instance) {
                        task_machine_name = NULL;
                        rc = ll_get_data(task_instance, 
                                         LL_TaskInstanceMachineName, 
                                         &task_machine_name);
                        if(0 != rc) {
                            opal_output(orte_ras_base.ras_output,
                                        "ras:loadleveler:allocate: ll_get_data:"
                                        " failure on LL_TaskInstanceMachineName"
                                        "RC= %d!", rc);
                            return ORTE_ERROR;
                        }
                        opal_argv_append(num_hosts, hostlist, task_machine_name);
                        task_instance = NULL;
                        rc = ll_get_data(task, LL_TaskGetNextTaskInstance, 
                                         &task_instance);
                        if(0 != rc) {
                            opal_output(orte_ras_base.ras_output,
                                        "ras:loadleveler:allocate: ll_get_data:"
                                        " failure on LL_TaskGetNextInstance. "
                                        "RC= %d!", rc);
                            return ORTE_ERROR;
                        }
                    }
                }
                task = NULL;
                if(0 != (rc = ll_get_data(node, LL_NodeGetNextTask, &task))) {
                    opal_output(orte_ras_base.ras_output,
                                "ras:loadleveler:allocate: ll_get_data: " 
                                "failure on LL_NodeGetNextTask. RC= %d!", rc);
                    return ORTE_ERROR;
                }
            }
            node = NULL;
            if(0 != (rc = ll_get_data(step, LL_StepGetNextNode, &node))) {
                opal_output(orte_ras_base.ras_output,
                            "ras:loadleveler:allocate: ll_get_data: failure "
                            "on LL_StepGetNextNode. RC= %d!", rc);
                return ORTE_ERROR;
            }
        }
    }
    ll_free_objs(queryObject);
    ll_deallocate(queryObject);

    return ORTE_SUCCESS;
}

#if 0
/* For now, we do not get the node architectures from LoadLeveler. It is slow,
 * and we don't even use the value. */
/*
 * get the machine arch from LoadLeveler
 * Will return NULL on error or a arch string that needs to be freed
 * (some code from the IBM documentation, licensed as above)
 */
static char* orte_ras_loadleveler_get_host_arch(char * hostname) {
    LL_element *queryObject, *machine; 
    int rc, obj_count, err_code;
    char * hostlist[2];
    char * arch;
  
    /* Initialize the query: Machine query */
    queryObject = ll_query(MACHINES);
    if(NULL == queryObject) {
        return NULL;
    } 
  
    /* Set query parameters: query specific machines by name */ 
    hostlist[0] = hostname;
    hostlist[1] = NULL; 
   
    rc = ll_set_request(queryObject, QUERY_HOST, hostlist, ALL_DATA); 
    if(0 != rc) { 
        return NULL;
    } 
  
    /* Get the machine objects from the LoadL_negotiator (central manager) daemon */ 
    machine = ll_get_objs(queryObject, LL_CM, NULL, &obj_count, &err_code); 
    if(NULL == machine || 1 != obj_count) {
        return NULL;
    } 
 
    /* Process the machine object */
    rc = ll_get_data(machine, LL_MachineArchitecture, &arch); 
    if(0 != rc) { 
        return NULL;
    } 
  
    /* Free objects obtained from Negotiator */ 
    ll_free_objs(queryObject); 
 
    /* Free query element */ 
    ll_deallocate(queryObject); 
    
    return arch;
}
#endif