Search in sources :

Example 1 with TopologyDisabledException

use of org.ow2.proactive.resourcemanager.frontend.topology.TopologyDisabledException in project scheduling by ow2-proactive.

the class SchedulingMethodImpl method getRMNodes.

/**
 * Ask to the RM the given number of node resources.<br>
 * If there is a problem with these task selection (such as bad selectionScript) this method
 * will terminate the corresponding tasks and jobs. As the selection scripts contain errors, the task
 * and its surrounding jobs must be stopped.
 *
 * @param neededResourcesNumber the number of resources to ask for (must be &gt; 0).
 * @param tasksToSchedule the task to be scheduled
 * @return A nodeSet that contains at most 'neededResourcesNumber' available compatible resources.
 * 		   An empty nodeSet if no nodes could be found
 * 		   null if the their was an exception when asking for the nodes (ie : selection script has failed)
 */
protected NodeSet getRMNodes(Map<JobId, JobDescriptor> jobMap, int neededResourcesNumber, LinkedList<EligibleTaskDescriptor> tasksToSchedule, Set<String> freeResources) {
    NodeSet nodeSet;
    if (neededResourcesNumber <= 0) {
        throw new IllegalArgumentException("'neededResourcesNumber' must be greater than 0");
    }
    EligibleTaskDescriptor etd = tasksToSchedule.getFirst();
    InternalJob currentJob = ((JobDescriptorImpl) jobMap.get(etd.getJobId())).getInternal();
    InternalTask internalTask0 = currentJob.getIHMTasks().get(etd.getTaskId());
    try {
        TopologyDescriptor descriptor = null;
        boolean bestEffort = true;
        if (internalTask0.isParallel()) {
            descriptor = internalTask0.getParallelEnvironment().getTopologyDescriptor();
            bestEffort = false;
            if (descriptor == null) {
                logger.debug("Topology is not defined for the task " + internalTask0.getName());
            }
        }
        if (descriptor == null) {
            // descriptor is not defined, use default
            descriptor = TopologyDescriptor.ARBITRARY;
        }
        try {
            Criteria criteria = new Criteria(neededResourcesNumber);
            criteria.setTopology(descriptor);
            // resolve script variables (if any) in the list of selection
            // scripts and then set it as the selection criteria.
            criteria.setScripts(resolveScriptVariables(internalTask0.getSelectionScripts(), internalTask0.getRuntimeVariables()));
            criteria.setBlackList(internalTask0.getNodeExclusion());
            criteria.setBestEffort(bestEffort);
            criteria.setAcceptableNodesUrls(freeResources);
            criteria.setBindings(createBindingsForSelectionScripts(currentJob, internalTask0));
            if (internalTask0.getRuntimeGenericInformation().containsKey(SchedulerConstants.NODE_ACCESS_TOKEN)) {
                criteria.setNodeAccessToken(internalTask0.getRuntimeGenericInformation().get(SchedulerConstants.NODE_ACCESS_TOKEN));
            }
            Collection<String> computationDescriptors = new ArrayList<>(tasksToSchedule.size());
            for (EligibleTaskDescriptor task : tasksToSchedule) {
                computationDescriptors.add(TaskLogger.getTaskLogRelativePath(task.getTaskId()));
            }
            criteria.setComputationDescriptors(computationDescriptors);
            nodeSet = getRMProxiesManager().getUserRMProxy(currentJob.getOwner(), currentJob.getCredentials()).getNodes(criteria);
        } catch (TopologyDisabledException tde) {
            jlogger.warn(currentJob.getId(), "will be canceled as the topology is disabled");
            schedulingService.simulateJobStartAndCancelIt(tasksToSchedule, "Topology is disabled");
            return null;
        }
        // the following line is used to unwrap the future, warning when moving or removing
        // it may also throw a ScriptException which is a RuntimeException
        PAFuture.waitFor(nodeSet, true);
        logger.debug("provided nodes " + nodeSet.size());
        return nodeSet;
    } catch (IOException | ClassNotFoundException e) {
        logger.warn("Failed to deserialize previous task variables before selection for task " + internalTask0.getId().toString(), e);
        schedulingService.simulateJobStartAndCancelIt(tasksToSchedule, "Failed to deserialize previous task variables before selection for task " + internalTask0.getId().toString());
        return null;
    } catch (RMProxyCreationException e) {
        logger.warn("Failed to create User RM Proxy", e);
        // simulate jobs starts and cancel it
        schedulingService.simulateJobStartAndCancelIt(tasksToSchedule, "Failed to create User RM Proxy : Authentication Failed to Resource Manager for user '" + currentJob.getOwner() + "'");
        // leave the method by ss failure
        return null;
    }
}
Also used : NodeSet(org.ow2.proactive.utils.NodeSet) InternalJob(org.ow2.proactive.scheduler.job.InternalJob) InternalTask(org.ow2.proactive.scheduler.task.internal.InternalTask) ArrayList(java.util.ArrayList) Criteria(org.ow2.proactive.utils.Criteria) IOException(java.io.IOException) JobDescriptorImpl(org.ow2.proactive.scheduler.descriptor.JobDescriptorImpl) EligibleTaskDescriptor(org.ow2.proactive.scheduler.descriptor.EligibleTaskDescriptor) RMProxyCreationException(org.ow2.proactive.scheduler.core.rmproxies.RMProxyCreationException) TopologyDisabledException(org.ow2.proactive.resourcemanager.frontend.topology.TopologyDisabledException) TopologyDescriptor(org.ow2.proactive.topology.descriptor.TopologyDescriptor)

Aggregations

IOException (java.io.IOException)1 ArrayList (java.util.ArrayList)1 TopologyDisabledException (org.ow2.proactive.resourcemanager.frontend.topology.TopologyDisabledException)1 RMProxyCreationException (org.ow2.proactive.scheduler.core.rmproxies.RMProxyCreationException)1 EligibleTaskDescriptor (org.ow2.proactive.scheduler.descriptor.EligibleTaskDescriptor)1 JobDescriptorImpl (org.ow2.proactive.scheduler.descriptor.JobDescriptorImpl)1 InternalJob (org.ow2.proactive.scheduler.job.InternalJob)1 InternalTask (org.ow2.proactive.scheduler.task.internal.InternalTask)1 TopologyDescriptor (org.ow2.proactive.topology.descriptor.TopologyDescriptor)1 Criteria (org.ow2.proactive.utils.Criteria)1 NodeSet (org.ow2.proactive.utils.NodeSet)1