Examples with YarnClusterMetrics org.apache.hadoop.yarn.api.records.YarnClusterMetrics used on opensource projects

Example 1 with YarnClusterMetrics

use of org.apache.hadoop.yarn.api.records.YarnClusterMetrics in project hadoop by apache.

the class TopCLI method getNodesInfo.

protected NodesInformation getNodesInfo() {
    NodesInformation nodeInfo = new NodesInformation();
    YarnClusterMetrics yarnClusterMetrics;
    try {
        yarnClusterMetrics = client.getYarnClusterMetrics();
    } catch (IOException ie) {
        LOG.error("Unable to fetch cluster metrics", ie);
        return nodeInfo;
    } catch (YarnException ye) {
        LOG.error("Unable to fetch cluster metrics", ye);
        return nodeInfo;
    }
    nodeInfo.decommissionedNodes = yarnClusterMetrics.getNumDecommissionedNodeManagers();
    nodeInfo.totalNodes = yarnClusterMetrics.getNumNodeManagers();
    nodeInfo.runningNodes = yarnClusterMetrics.getNumActiveNodeManagers();
    nodeInfo.lostNodes = yarnClusterMetrics.getNumLostNodeManagers();
    nodeInfo.unhealthyNodes = yarnClusterMetrics.getNumUnhealthyNodeManagers();
    nodeInfo.rebootedNodes = yarnClusterMetrics.getNumRebootedNodeManagers();
    return nodeInfo;
}

Example 2 with YarnClusterMetrics

use of org.apache.hadoop.yarn.api.records.YarnClusterMetrics in project hadoop by apache.

the class ResourceMgrDelegate method getClusterMetrics.

public ClusterMetrics getClusterMetrics() throws IOException, InterruptedException {
    try {
        YarnClusterMetrics metrics = client.getYarnClusterMetrics();
        ClusterMetrics oldMetrics = new ClusterMetrics(1, 1, 1, 1, 1, 1, metrics.getNumNodeManagers() * 10, metrics.getNumNodeManagers() * 2, 1, metrics.getNumNodeManagers(), 0, 0);
        return oldMetrics;
    } catch (YarnException e) {
        throw new IOException(e);
    }
}

Example 3 with YarnClusterMetrics

use of org.apache.hadoop.yarn.api.records.YarnClusterMetrics in project hadoop by apache.

the class Client method run.

/**
   * Main run function for the client
   * @return true if application completed successfully
   * @throws IOException
   * @throws YarnException
   */
public boolean run() throws IOException, YarnException {
    LOG.info("Running Client");
    yarnClient.start();
    YarnClusterMetrics clusterMetrics = yarnClient.getYarnClusterMetrics();
    LOG.info("Got Cluster metric info from ASM" + ", numNodeManagers=" + clusterMetrics.getNumNodeManagers());
    List<NodeReport> clusterNodeReports = yarnClient.getNodeReports(NodeState.RUNNING);
    LOG.info("Got Cluster node info from ASM");
    for (NodeReport node : clusterNodeReports) {
        LOG.info("Got node report from ASM for" + ", nodeId=" + node.getNodeId() + ", nodeAddress=" + node.getHttpAddress() + ", nodeRackName=" + node.getRackName() + ", nodeNumContainers=" + node.getNumContainers());
    }
    QueueInfo queueInfo = yarnClient.getQueueInfo(this.amQueue);
    LOG.info("Queue info" + ", queueName=" + queueInfo.getQueueName() + ", queueCurrentCapacity=" + queueInfo.getCurrentCapacity() + ", queueMaxCapacity=" + queueInfo.getMaximumCapacity() + ", queueApplicationCount=" + queueInfo.getApplications().size() + ", queueChildQueueCount=" + queueInfo.getChildQueues().size());
    List<QueueUserACLInfo> listAclInfo = yarnClient.getQueueAclsInfo();
    for (QueueUserACLInfo aclInfo : listAclInfo) {
        for (QueueACL userAcl : aclInfo.getUserAcls()) {
            LOG.info("User ACL Info for Queue" + ", queueName=" + aclInfo.getQueueName() + ", userAcl=" + userAcl.name());
        }
    }
    if (domainId != null && domainId.length() > 0 && toCreateDomain) {
        prepareTimelineDomain();
    }
    // Get a new application id
    YarnClientApplication app = yarnClient.createApplication();
    GetNewApplicationResponse appResponse = app.getNewApplicationResponse();
    // TODO get min/max resource capabilities from RM and change memory ask if needed
    // If we do not have min/max, we may not be able to correctly request 
    // the required resources from the RM for the app master
    // Memory ask has to be a multiple of min and less than max. 
    // Dump out information about cluster capability as seen by the resource manager
    long maxMem = appResponse.getMaximumResourceCapability().getMemorySize();
    LOG.info("Max mem capability of resources in this cluster " + maxMem);
    // A resource ask cannot exceed the max. 
    if (amMemory > maxMem) {
        LOG.info("AM memory specified above max threshold of cluster. Using max value." + ", specified=" + amMemory + ", max=" + maxMem);
        amMemory = maxMem;
    }
    int maxVCores = appResponse.getMaximumResourceCapability().getVirtualCores();
    LOG.info("Max virtual cores capability of resources in this cluster " + maxVCores);
    if (amVCores > maxVCores) {
        LOG.info("AM virtual cores specified above max threshold of cluster. " + "Using max value." + ", specified=" + amVCores + ", max=" + maxVCores);
        amVCores = maxVCores;
    }
    // set the application name
    ApplicationSubmissionContext appContext = app.getApplicationSubmissionContext();
    ApplicationId appId = appContext.getApplicationId();
    appContext.setKeepContainersAcrossApplicationAttempts(keepContainers);
    appContext.setApplicationName(appName);
    if (attemptFailuresValidityInterval >= 0) {
        appContext.setAttemptFailuresValidityInterval(attemptFailuresValidityInterval);
    }
    Set<String> tags = new HashSet<String>();
    if (flowName != null) {
        tags.add(TimelineUtils.generateFlowNameTag(flowName));
    }
    if (flowVersion != null) {
        tags.add(TimelineUtils.generateFlowVersionTag(flowVersion));
    }
    if (flowRunId != 0) {
        tags.add(TimelineUtils.generateFlowRunIdTag(flowRunId));
    }
    appContext.setApplicationTags(tags);
    // set local resources for the application master
    // local files or archives as needed
    // In this scenario, the jar file for the application master is part of the local resources			
    Map<String, LocalResource> localResources = new HashMap<String, LocalResource>();
    LOG.info("Copy App Master jar from local filesystem and add to local environment");
    // Copy the application master jar to the filesystem 
    // Create a local resource to point to the destination jar path 
    FileSystem fs = FileSystem.get(conf);
    addToLocalResources(fs, appMasterJar, appMasterJarPath, appId.toString(), localResources, null);
    // Set the log4j properties if needed 
    if (!log4jPropFile.isEmpty()) {
        addToLocalResources(fs, log4jPropFile, log4jPath, appId.toString(), localResources, null);
    }
    // The shell script has to be made available on the final container(s)
    // where it will be executed. 
    // To do this, we need to first copy into the filesystem that is visible 
    // to the yarn framework. 
    // We do not need to set this as a local resource for the application 
    // master as the application master does not need it. 		
    String hdfsShellScriptLocation = "";
    long hdfsShellScriptLen = 0;
    long hdfsShellScriptTimestamp = 0;
    if (!shellScriptPath.isEmpty()) {
        Path shellSrc = new Path(shellScriptPath);
        String shellPathSuffix = appName + "/" + appId.toString() + "/" + SCRIPT_PATH;
        Path shellDst = new Path(fs.getHomeDirectory(), shellPathSuffix);
        fs.copyFromLocalFile(false, true, shellSrc, shellDst);
        hdfsShellScriptLocation = shellDst.toUri().toString();
        FileStatus shellFileStatus = fs.getFileStatus(shellDst);
        hdfsShellScriptLen = shellFileStatus.getLen();
        hdfsShellScriptTimestamp = shellFileStatus.getModificationTime();
    }
    if (!shellCommand.isEmpty()) {
        addToLocalResources(fs, null, shellCommandPath, appId.toString(), localResources, shellCommand);
    }
    if (shellArgs.length > 0) {
        addToLocalResources(fs, null, shellArgsPath, appId.toString(), localResources, StringUtils.join(shellArgs, " "));
    }
    // Set the necessary security tokens as needed
    //amContainer.setContainerTokens(containerToken);
    // Set the env variables to be setup in the env where the application master will be run
    LOG.info("Set the environment for the application master");
    Map<String, String> env = new HashMap<String, String>();
    // put location of shell script into env
    // using the env info, the application master will create the correct local resource for the 
    // eventual containers that will be launched to execute the shell scripts
    env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTLOCATION, hdfsShellScriptLocation);
    env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTTIMESTAMP, Long.toString(hdfsShellScriptTimestamp));
    env.put(DSConstants.DISTRIBUTEDSHELLSCRIPTLEN, Long.toString(hdfsShellScriptLen));
    if (domainId != null && domainId.length() > 0) {
        env.put(DSConstants.DISTRIBUTEDSHELLTIMELINEDOMAIN, domainId);
    }
    // Add AppMaster.jar location to classpath 		
    // At some point we should not be required to add 
    // the hadoop specific classpaths to the env. 
    // It should be provided out of the box. 
    // For now setting all required classpaths including
    // the classpath to "." for the application jar
    StringBuilder classPathEnv = new StringBuilder(Environment.CLASSPATH.$$()).append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./*");
    for (String c : conf.getStrings(YarnConfiguration.YARN_APPLICATION_CLASSPATH, YarnConfiguration.DEFAULT_YARN_CROSS_PLATFORM_APPLICATION_CLASSPATH)) {
        classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR);
        classPathEnv.append(c.trim());
    }
    classPathEnv.append(ApplicationConstants.CLASS_PATH_SEPARATOR).append("./log4j.properties");
    // add the runtime classpath needed for tests to work
    if (conf.getBoolean(YarnConfiguration.IS_MINI_YARN_CLUSTER, false)) {
        classPathEnv.append(':');
        classPathEnv.append(System.getProperty("java.class.path"));
    }
    env.put("CLASSPATH", classPathEnv.toString());
    // Set the necessary command to execute the application master 
    Vector<CharSequence> vargs = new Vector<CharSequence>(30);
    // Set java executable command 
    LOG.info("Setting up app master command");
    vargs.add(Environment.JAVA_HOME.$$() + "/bin/java");
    // Set Xmx based on am memory size
    vargs.add("-Xmx" + amMemory + "m");
    // Set class name 
    vargs.add(appMasterMainClass);
    // Set params for Application Master
    vargs.add("--container_memory " + String.valueOf(containerMemory));
    vargs.add("--container_vcores " + String.valueOf(containerVirtualCores));
    vargs.add("--num_containers " + String.valueOf(numContainers));
    if (null != nodeLabelExpression) {
        appContext.setNodeLabelExpression(nodeLabelExpression);
    }
    vargs.add("--priority " + String.valueOf(shellCmdPriority));
    for (Map.Entry<String, String> entry : shellEnv.entrySet()) {
        vargs.add("--shell_env " + entry.getKey() + "=" + entry.getValue());
    }
    if (debugFlag) {
        vargs.add("--debug");
    }
    vargs.addAll(containerRetryOptions);
    vargs.add("1>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stdout");
    vargs.add("2>" + ApplicationConstants.LOG_DIR_EXPANSION_VAR + "/AppMaster.stderr");
    // Get final commmand
    StringBuilder command = new StringBuilder();
    for (CharSequence str : vargs) {
        command.append(str).append(" ");
    }
    LOG.info("Completed setting up app master command " + command.toString());
    List<String> commands = new ArrayList<String>();
    commands.add(command.toString());
    // Set up the container launch context for the application master
    ContainerLaunchContext amContainer = ContainerLaunchContext.newInstance(localResources, env, commands, null, null, null);
    // Set up resource type requirements
    // For now, both memory and vcores are supported, so we set memory and 
    // vcores requirements
    Resource capability = Resource.newInstance(amMemory, amVCores);
    appContext.setResource(capability);
    // Setup security tokens
    if (UserGroupInformation.isSecurityEnabled()) {
        // Note: Credentials class is marked as LimitedPrivate for HDFS and MapReduce
        Credentials credentials = new Credentials();
        String tokenRenewer = YarnClientUtils.getRmPrincipal(conf);
        if (tokenRenewer == null || tokenRenewer.length() == 0) {
            throw new IOException("Can't get Master Kerberos principal for the RM to use as renewer");
        }
        // For now, only getting tokens for the default file-system.
        final Token<?>[] tokens = fs.addDelegationTokens(tokenRenewer, credentials);
        if (tokens != null) {
            for (Token<?> token : tokens) {
                LOG.info("Got dt for " + fs.getUri() + "; " + token);
            }
        }
        DataOutputBuffer dob = new DataOutputBuffer();
        credentials.writeTokenStorageToStream(dob);
        ByteBuffer fsTokens = ByteBuffer.wrap(dob.getData(), 0, dob.getLength());
        amContainer.setTokens(fsTokens);
    }
    appContext.setAMContainerSpec(amContainer);
    // Set the priority for the application master
    // TODO - what is the range for priority? how to decide? 
    Priority pri = Priority.newInstance(amPriority);
    appContext.setPriority(pri);
    // Set the queue to which this application is to be submitted in the RM
    appContext.setQueue(amQueue);
    // Submit the application to the applications manager
    // SubmitApplicationResponse submitResp = applicationsManager.submitApplication(appRequest);
    // Ignore the response as either a valid response object is returned on success 
    // or an exception thrown to denote some form of a failure
    LOG.info("Submitting application to ASM");
    yarnClient.submitApplication(appContext);
    // Monitor the application
    return monitorApplication(appId);
}

Example 4 with YarnClusterMetrics

use of org.apache.hadoop.yarn.api.records.YarnClusterMetrics in project flink by apache.

the class AbstractYarnClusterDescriptor method getClusterDescription.

@Override
public String getClusterDescription() {
    try {
        ByteArrayOutputStream baos = new ByteArrayOutputStream();
        PrintStream ps = new PrintStream(baos);
        YarnClient yarnClient = getYarnClient();
        YarnClusterMetrics metrics = yarnClient.getYarnClusterMetrics();
        ps.append("NodeManagers in the ClusterClient " + metrics.getNumNodeManagers());
        List<NodeReport> nodes = yarnClient.getNodeReports(NodeState.RUNNING);
        final String format = "|%-16s |%-16s %n";
        ps.printf("|Property         |Value          %n");
        ps.println("+---------------------------------------+");
        int totalMemory = 0;
        int totalCores = 0;
        for (NodeReport rep : nodes) {
            final Resource res = rep.getCapability();
            totalMemory += res.getMemory();
            totalCores += res.getVirtualCores();
            ps.format(format, "NodeID", rep.getNodeId());
            ps.format(format, "Memory", res.getMemory() + " MB");
            ps.format(format, "vCores", res.getVirtualCores());
            ps.format(format, "HealthReport", rep.getHealthReport());
            ps.format(format, "Containers", rep.getNumContainers());
            ps.println("+---------------------------------------+");
        }
        ps.println("Summary: totalMemory " + totalMemory + " totalCores " + totalCores);
        List<QueueInfo> qInfo = yarnClient.getAllQueues();
        for (QueueInfo q : qInfo) {
            ps.println("Queue: " + q.getQueueName() + ", Current Capacity: " + q.getCurrentCapacity() + " Max Capacity: " + q.getMaximumCapacity() + " Applications: " + q.getApplications().size());
        }
        yarnClient.stop();
        return baos.toString();
    } catch (Exception e) {
        throw new RuntimeException("Couldn't get cluster description", e);
    }
}

Example 5 with YarnClusterMetrics

use of org.apache.hadoop.yarn.api.records.YarnClusterMetrics in project tez by apache.

the class ResourceMgrDelegate method getClusterMetrics.

public ClusterMetrics getClusterMetrics() throws IOException, InterruptedException {
    YarnClusterMetrics metrics;
    try {
        metrics = client.getYarnClusterMetrics();
    } catch (YarnException e) {
        throw new IOException(e);
    }
    ClusterMetrics oldMetrics = new ClusterMetrics(1, 1, 1, 1, 1, 1, metrics.getNumNodeManagers() * 10, metrics.getNumNodeManagers() * 2, 1, metrics.getNumNodeManagers(), 0, 0);
    return oldMetrics;
}