Examples with YarnRuntimeException org.apache.hadoop.yarn.exceptions.YarnRuntimeException used on opensource projects

Example 11 with YarnRuntimeException

use of org.apache.hadoop.yarn.exceptions.YarnRuntimeException in project hadoop by apache.

the class JobHistoryEventHandler method handleEvent.

@Private
public void handleEvent(JobHistoryEvent event) {
    synchronized (lock) {
        // If this is JobSubmitted Event, setup the writer
        if (event.getHistoryEvent().getEventType() == EventType.AM_STARTED) {
            try {
                AMStartedEvent amStartedEvent = (AMStartedEvent) event.getHistoryEvent();
                setupEventWriter(event.getJobID(), amStartedEvent);
            } catch (IOException ioe) {
                LOG.error("Error JobHistoryEventHandler in handleEvent: " + event, ioe);
                throw new YarnRuntimeException(ioe);
            }
        }
        // For all events
        // (1) Write it out
        // (2) Process it for JobSummary
        // (3) Process it for ATS (if enabled)
        MetaInfo mi = fileMap.get(event.getJobID());
        try {
            HistoryEvent historyEvent = event.getHistoryEvent();
            if (!(historyEvent instanceof NormalizedResourceEvent)) {
                mi.writeEvent(historyEvent);
            }
            processEventForJobSummary(event.getHistoryEvent(), mi.getJobSummary(), event.getJobID());
            if (timelineV2Client != null) {
                processEventForNewTimelineService(historyEvent, event.getJobID(), event.getTimestamp());
            } else if (timelineClient != null) {
                processEventForTimelineServer(historyEvent, event.getJobID(), event.getTimestamp());
            }
            if (LOG.isDebugEnabled()) {
                LOG.debug("In HistoryEventHandler " + event.getHistoryEvent().getEventType());
            }
        } catch (IOException e) {
            LOG.error("Error writing History Event: " + event.getHistoryEvent(), e);
            throw new YarnRuntimeException(e);
        }
        if (event.getHistoryEvent().getEventType() == EventType.JOB_SUBMITTED) {
            JobSubmittedEvent jobSubmittedEvent = (JobSubmittedEvent) event.getHistoryEvent();
            mi.getJobIndexInfo().setSubmitTime(jobSubmittedEvent.getSubmitTime());
            mi.getJobIndexInfo().setQueueName(jobSubmittedEvent.getJobQueueName());
        }
        //initialize the launchTime in the JobIndexInfo of MetaInfo
        if (event.getHistoryEvent().getEventType() == EventType.JOB_INITED) {
            JobInitedEvent jie = (JobInitedEvent) event.getHistoryEvent();
            mi.getJobIndexInfo().setJobStartTime(jie.getLaunchTime());
        }
        if (event.getHistoryEvent().getEventType() == EventType.JOB_QUEUE_CHANGED) {
            JobQueueChangeEvent jQueueEvent = (JobQueueChangeEvent) event.getHistoryEvent();
            mi.getJobIndexInfo().setQueueName(jQueueEvent.getJobQueueName());
        }
        // If this is JobFinishedEvent, close the writer and setup the job-index
        if (event.getHistoryEvent().getEventType() == EventType.JOB_FINISHED) {
            try {
                JobFinishedEvent jFinishedEvent = (JobFinishedEvent) event.getHistoryEvent();
                mi.getJobIndexInfo().setFinishTime(jFinishedEvent.getFinishTime());
                mi.getJobIndexInfo().setNumMaps(jFinishedEvent.getFinishedMaps());
                mi.getJobIndexInfo().setNumReduces(jFinishedEvent.getFinishedReduces());
                mi.getJobIndexInfo().setJobStatus(JobState.SUCCEEDED.toString());
                closeEventWriter(event.getJobID());
                processDoneFiles(event.getJobID());
            } catch (IOException e) {
                throw new YarnRuntimeException(e);
            }
        }
        // summary, job history file etc.) if it is last AM retry.
        if (event.getHistoryEvent().getEventType() == EventType.JOB_ERROR) {
            try {
                JobUnsuccessfulCompletionEvent jucEvent = (JobUnsuccessfulCompletionEvent) event.getHistoryEvent();
                mi.getJobIndexInfo().setFinishTime(jucEvent.getFinishTime());
                mi.getJobIndexInfo().setNumMaps(jucEvent.getFinishedMaps());
                mi.getJobIndexInfo().setNumReduces(jucEvent.getFinishedReduces());
                mi.getJobIndexInfo().setJobStatus(jucEvent.getStatus());
                closeEventWriter(event.getJobID());
                if (context.isLastAMRetry())
                    processDoneFiles(event.getJobID());
            } catch (IOException e) {
                throw new YarnRuntimeException(e);
            }
        }
        if (event.getHistoryEvent().getEventType() == EventType.JOB_FAILED || event.getHistoryEvent().getEventType() == EventType.JOB_KILLED) {
            try {
                JobUnsuccessfulCompletionEvent jucEvent = (JobUnsuccessfulCompletionEvent) event.getHistoryEvent();
                mi.getJobIndexInfo().setFinishTime(jucEvent.getFinishTime());
                mi.getJobIndexInfo().setNumMaps(jucEvent.getFinishedMaps());
                mi.getJobIndexInfo().setNumReduces(jucEvent.getFinishedReduces());
                mi.getJobIndexInfo().setJobStatus(jucEvent.getStatus());
                closeEventWriter(event.getJobID());
                processDoneFiles(event.getJobID());
            } catch (IOException e) {
                throw new YarnRuntimeException(e);
            }
        }
    }
}

Example 12 with YarnRuntimeException

use of org.apache.hadoop.yarn.exceptions.YarnRuntimeException in project hadoop by apache.

the class MRAppMaster method serviceInit.

@Override
protected void serviceInit(final Configuration conf) throws Exception {
    // create the job classloader if enabled
    createJobClassLoader(conf);
    conf.setBoolean(Dispatcher.DISPATCHER_EXIT_ON_ERROR_KEY, true);
    initJobCredentialsAndUGI(conf);
    dispatcher = createDispatcher();
    addIfService(dispatcher);
    taskAttemptFinishingMonitor = createTaskAttemptFinishingMonitor(dispatcher.getEventHandler());
    addIfService(taskAttemptFinishingMonitor);
    context = new RunningAppContext(conf, taskAttemptFinishingMonitor);
    // Job name is the same as the app name util we support DAG of jobs
    // for an app later
    appName = conf.get(MRJobConfig.JOB_NAME, "<missing app name>");
    conf.setInt(MRJobConfig.APPLICATION_ATTEMPT_ID, appAttemptID.getAttemptId());
    newApiCommitter = false;
    jobId = MRBuilderUtils.newJobId(appAttemptID.getApplicationId(), appAttemptID.getApplicationId().getId());
    int numReduceTasks = conf.getInt(MRJobConfig.NUM_REDUCES, 0);
    if ((numReduceTasks > 0 && conf.getBoolean("mapred.reducer.new-api", false)) || (numReduceTasks == 0 && conf.getBoolean("mapred.mapper.new-api", false))) {
        newApiCommitter = true;
        LOG.info("Using mapred newApiCommitter.");
    }
    boolean copyHistory = false;
    committer = createOutputCommitter(conf);
    try {
        String user = UserGroupInformation.getCurrentUser().getShortUserName();
        Path stagingDir = MRApps.getStagingAreaDir(conf, user);
        FileSystem fs = getFileSystem(conf);
        boolean stagingExists = fs.exists(stagingDir);
        Path startCommitFile = MRApps.getStartJobCommitFile(conf, user, jobId);
        boolean commitStarted = fs.exists(startCommitFile);
        Path endCommitSuccessFile = MRApps.getEndJobCommitSuccessFile(conf, user, jobId);
        boolean commitSuccess = fs.exists(endCommitSuccessFile);
        Path endCommitFailureFile = MRApps.getEndJobCommitFailureFile(conf, user, jobId);
        boolean commitFailure = fs.exists(endCommitFailureFile);
        if (!stagingExists) {
            isLastAMRetry = true;
            LOG.info("Attempt num: " + appAttemptID.getAttemptId() + " is last retry: " + isLastAMRetry + " because the staging dir doesn't exist.");
            errorHappenedShutDown = true;
            forcedState = JobStateInternal.ERROR;
            shutDownMessage = "Staging dir does not exist " + stagingDir;
            LOG.fatal(shutDownMessage);
        } else if (commitStarted) {
            //A commit was started so this is the last time, we just need to know
            // what result we will use to notify, and how we will unregister
            errorHappenedShutDown = true;
            isLastAMRetry = true;
            LOG.info("Attempt num: " + appAttemptID.getAttemptId() + " is last retry: " + isLastAMRetry + " because a commit was started.");
            copyHistory = true;
            if (commitSuccess) {
                shutDownMessage = "Job commit succeeded in a prior MRAppMaster attempt " + "before it crashed. Recovering.";
                forcedState = JobStateInternal.SUCCEEDED;
            } else if (commitFailure) {
                shutDownMessage = "Job commit failed in a prior MRAppMaster attempt " + "before it crashed. Not retrying.";
                forcedState = JobStateInternal.FAILED;
            } else {
                if (isCommitJobRepeatable()) {
                    // cleanup previous half done commits if committer supports
                    // repeatable job commit.
                    errorHappenedShutDown = false;
                    cleanupInterruptedCommit(conf, fs, startCommitFile);
                } else {
                    //The commit is still pending, commit error
                    shutDownMessage = "Job commit from a prior MRAppMaster attempt is " + "potentially in progress. Preventing multiple commit executions";
                    forcedState = JobStateInternal.ERROR;
                }
            }
        }
    } catch (IOException e) {
        throw new YarnRuntimeException("Error while initializing", e);
    }
    if (errorHappenedShutDown) {
        NoopEventHandler eater = new NoopEventHandler();
        //We do not have a JobEventDispatcher in this path
        dispatcher.register(JobEventType.class, eater);
        EventHandler<JobHistoryEvent> historyService = null;
        if (copyHistory) {
            historyService = createJobHistoryHandler(context);
            dispatcher.register(org.apache.hadoop.mapreduce.jobhistory.EventType.class, historyService);
        } else {
            dispatcher.register(org.apache.hadoop.mapreduce.jobhistory.EventType.class, eater);
        }
        if (copyHistory) {
            // Now that there's a FINISHING state for application on RM to give AMs
            // plenty of time to clean up after unregister it's safe to clean staging
            // directory after unregistering with RM. So, we start the staging-dir
            // cleaner BEFORE the ContainerAllocator so that on shut-down,
            // ContainerAllocator unregisters first and then the staging-dir cleaner
            // deletes staging directory.
            addService(createStagingDirCleaningService());
        }
        // service to allocate containers from RM (if non-uber) or to fake it (uber)
        containerAllocator = createContainerAllocator(null, context);
        addIfService(containerAllocator);
        dispatcher.register(ContainerAllocator.EventType.class, containerAllocator);
        if (copyHistory) {
            // Add the JobHistoryEventHandler last so that it is properly stopped first.
            // This will guarantee that all history-events are flushed before AM goes
            // ahead with shutdown.
            // Note: Even though JobHistoryEventHandler is started last, if any
            // component creates a JobHistoryEvent in the meanwhile, it will be just be
            // queued inside the JobHistoryEventHandler 
            addIfService(historyService);
            JobHistoryCopyService cpHist = new JobHistoryCopyService(appAttemptID, dispatcher.getEventHandler());
            addIfService(cpHist);
        }
    } else {
        //service to handle requests from JobClient
        clientService = createClientService(context);
        // Init ClientService separately so that we stop it separately, since this
        // service needs to wait some time before it stops so clients can know the
        // final states
        clientService.init(conf);
        containerAllocator = createContainerAllocator(clientService, context);
        //service to handle the output committer
        committerEventHandler = createCommitterEventHandler(context, committer);
        addIfService(committerEventHandler);
        //policy handling preemption requests from RM
        callWithJobClassLoader(conf, new Action<Void>() {

            public Void call(Configuration conf) {
                preemptionPolicy = createPreemptionPolicy(conf);
                preemptionPolicy.init(context);
                return null;
            }
        });
        //service to handle requests to TaskUmbilicalProtocol
        taskAttemptListener = createTaskAttemptListener(context, preemptionPolicy);
        addIfService(taskAttemptListener);
        //service to log job history events
        EventHandler<JobHistoryEvent> historyService = createJobHistoryHandler(context);
        dispatcher.register(org.apache.hadoop.mapreduce.jobhistory.EventType.class, historyService);
        this.jobEventDispatcher = new JobEventDispatcher();
        //register the event dispatchers
        dispatcher.register(JobEventType.class, jobEventDispatcher);
        dispatcher.register(TaskEventType.class, new TaskEventDispatcher());
        dispatcher.register(TaskAttemptEventType.class, new TaskAttemptEventDispatcher());
        dispatcher.register(CommitterEventType.class, committerEventHandler);
        if (conf.getBoolean(MRJobConfig.MAP_SPECULATIVE, false) || conf.getBoolean(MRJobConfig.REDUCE_SPECULATIVE, false)) {
            //optional service to speculate on task attempts' progress
            speculator = createSpeculator(conf, context);
            addIfService(speculator);
        }
        speculatorEventDispatcher = new SpeculatorEventDispatcher(conf);
        dispatcher.register(Speculator.EventType.class, speculatorEventDispatcher);
        // Now that there's a FINISHING state for application on RM to give AMs
        // plenty of time to clean up after unregister it's safe to clean staging
        // directory after unregistering with RM. So, we start the staging-dir
        // cleaner BEFORE the ContainerAllocator so that on shut-down,
        // ContainerAllocator unregisters first and then the staging-dir cleaner
        // deletes staging directory.
        addService(createStagingDirCleaningService());
        // service to allocate containers from RM (if non-uber) or to fake it (uber)
        addIfService(containerAllocator);
        dispatcher.register(ContainerAllocator.EventType.class, containerAllocator);
        // corresponding service to launch allocated containers via NodeManager
        containerLauncher = createContainerLauncher(context);
        addIfService(containerLauncher);
        dispatcher.register(ContainerLauncher.EventType.class, containerLauncher);
        // Add the JobHistoryEventHandler last so that it is properly stopped first.
        // This will guarantee that all history-events are flushed before AM goes
        // ahead with shutdown.
        // Note: Even though JobHistoryEventHandler is started last, if any
        // component creates a JobHistoryEvent in the meanwhile, it will be just be
        // queued inside the JobHistoryEventHandler 
        addIfService(historyService);
    }
    super.serviceInit(conf);
}

Example 13 with YarnRuntimeException

use of org.apache.hadoop.yarn.exceptions.YarnRuntimeException in project hadoop by apache.

the class MRAppMaster method initJobCredentialsAndUGI.

// end createJob()
/**
   * Obtain the tokens needed by the job and put them in the UGI
   * @param conf
   */
protected void initJobCredentialsAndUGI(Configuration conf) {
    try {
        this.currentUser = UserGroupInformation.getCurrentUser();
        this.jobCredentials = ((JobConf) conf).getCredentials();
        if (CryptoUtils.isEncryptedSpillEnabled(conf)) {
            int keyLen = conf.getInt(MRJobConfig.MR_ENCRYPTED_INTERMEDIATE_DATA_KEY_SIZE_BITS, MRJobConfig.DEFAULT_MR_ENCRYPTED_INTERMEDIATE_DATA_KEY_SIZE_BITS);
            KeyGenerator keyGen = KeyGenerator.getInstance(INTERMEDIATE_DATA_ENCRYPTION_ALGO);
            keyGen.init(keyLen);
            encryptedSpillKey = keyGen.generateKey().getEncoded();
        } else {
            encryptedSpillKey = new byte[] { 0 };
        }
    } catch (IOException e) {
        throw new YarnRuntimeException(e);
    } catch (NoSuchAlgorithmException e) {
        throw new YarnRuntimeException(e);
    }
}

Example 14 with YarnRuntimeException

use of org.apache.hadoop.yarn.exceptions.YarnRuntimeException in project hadoop by apache.

the class TaskAttemptListenerImpl method startRpcServer.

protected void startRpcServer() {
    Configuration conf = getConfig();
    try {
        server = new RPC.Builder(conf).setProtocol(TaskUmbilicalProtocol.class).setInstance(this).setBindAddress("0.0.0.0").setPortRangeConfig(MRJobConfig.MR_AM_JOB_CLIENT_PORT_RANGE).setNumHandlers(conf.getInt(MRJobConfig.MR_AM_TASK_LISTENER_THREAD_COUNT, MRJobConfig.DEFAULT_MR_AM_TASK_LISTENER_THREAD_COUNT)).setVerbose(false).setSecretManager(jobTokenSecretManager).build();
        // Enable service authorization?
        if (conf.getBoolean(CommonConfigurationKeysPublic.HADOOP_SECURITY_AUTHORIZATION, false)) {
            refreshServiceAcls(conf, new MRAMPolicyProvider());
        }
        server.start();
        this.address = NetUtils.createSocketAddrForHost(context.getNMHostname(), server.getListenerAddress().getPort());
    } catch (IOException e) {
        throw new YarnRuntimeException(e);
    }
}

Example 15 with YarnRuntimeException

use of org.apache.hadoop.yarn.exceptions.YarnRuntimeException in project hadoop by apache.

the class ContainerManagerImpl method handle.

@SuppressWarnings("unchecked")
@Override
public void handle(ContainerManagerEvent event) {
    switch(event.getType()) {
        case FINISH_APPS:
            CMgrCompletedAppsEvent appsFinishedEvent = (CMgrCompletedAppsEvent) event;
            for (ApplicationId appID : appsFinishedEvent.getAppsToCleanup()) {
                Application app = this.context.getApplications().get(appID);
                if (app == null) {
                    LOG.warn("couldn't find application " + appID + " while processing" + " FINISH_APPS event");
                    continue;
                }
                boolean shouldDropEvent = false;
                for (Container container : app.getContainers().values()) {
                    if (container.isRecovering()) {
                        LOG.info("drop FINISH_APPS event to " + appID + " because " + "container " + container.getContainerId() + " is recovering");
                        shouldDropEvent = true;
                        break;
                    }
                }
                if (shouldDropEvent) {
                    continue;
                }
                String diagnostic = "";
                if (appsFinishedEvent.getReason() == CMgrCompletedAppsEvent.Reason.ON_SHUTDOWN) {
                    diagnostic = "Application killed on shutdown";
                } else if (appsFinishedEvent.getReason() == CMgrCompletedAppsEvent.Reason.BY_RESOURCEMANAGER) {
                    diagnostic = "Application killed by ResourceManager";
                }
                this.dispatcher.getEventHandler().handle(new ApplicationFinishEvent(appID, diagnostic));
            }
            break;
        case FINISH_CONTAINERS:
            CMgrCompletedContainersEvent containersFinishedEvent = (CMgrCompletedContainersEvent) event;
            for (ContainerId containerId : containersFinishedEvent.getContainersToCleanup()) {
                ApplicationId appId = containerId.getApplicationAttemptId().getApplicationId();
                Application app = this.context.getApplications().get(appId);
                if (app == null) {
                    LOG.warn("couldn't find app " + appId + " while processing" + " FINISH_CONTAINERS event");
                    continue;
                }
                Container container = app.getContainers().get(containerId);
                if (container == null) {
                    LOG.warn("couldn't find container " + containerId + " while processing FINISH_CONTAINERS event");
                    continue;
                }
                if (container.isRecovering()) {
                    LOG.info("drop FINISH_CONTAINERS event to " + containerId + " because container is recovering");
                    continue;
                }
                this.dispatcher.getEventHandler().handle(new ContainerKillEvent(containerId, ContainerExitStatus.KILLED_BY_RESOURCEMANAGER, "Container Killed by ResourceManager"));
            }
            break;
        case DECREASE_CONTAINERS_RESOURCE:
            CMgrDecreaseContainersResourceEvent containersDecreasedEvent = (CMgrDecreaseContainersResourceEvent) event;
            for (org.apache.hadoop.yarn.api.records.Container container : containersDecreasedEvent.getContainersToDecrease()) {
                try {
                    changeContainerResourceInternal(container.getId(), container.getVersion(), container.getResource(), false);
                } catch (YarnException e) {
                    LOG.error("Unable to decrease container resource", e);
                } catch (IOException e) {
                    LOG.error("Unable to update container resource in store", e);
                }
            }
            break;
        case SIGNAL_CONTAINERS:
            CMgrSignalContainersEvent containersSignalEvent = (CMgrSignalContainersEvent) event;
            for (SignalContainerRequest request : containersSignalEvent.getContainersToSignal()) {
                internalSignalToContainer(request, "ResourceManager");
            }
            break;
        default:
            throw new YarnRuntimeException("Got an unknown ContainerManagerEvent type: " + event.getType());
    }
}