Search in sources :

Example 6 with ProgramContextAware

use of io.cdap.cdap.data.ProgramContextAware in project cdap by cdapio.

the class SparkProgramRunner method run.

@Override
public ProgramController run(Program program, ProgramOptions options) {
    LOG.trace("Starting Spark program {} with SparkProgramRunner of ClassLoader {}", program.getId(), getClass().getClassLoader());
    // Get the RunId first. It is used for the creation of the ClassLoader closing thread.
    Arguments arguments = options.getArguments();
    RunId runId = ProgramRunners.getRunId(options);
    Deque<Closeable> closeables = new LinkedList<>();
    try {
        // Extract and verify parameters
        ApplicationSpecification appSpec = program.getApplicationSpecification();
        Preconditions.checkNotNull(appSpec, "Missing application specification.");
        ProgramType processorType = program.getType();
        Preconditions.checkNotNull(processorType, "Missing processor type.");
        Preconditions.checkArgument(processorType == ProgramType.SPARK, "Only Spark process type is supported.");
        SparkSpecification spec = appSpec.getSpark().get(program.getName());
        Preconditions.checkNotNull(spec, "Missing SparkSpecification for %s", program.getName());
        String host = options.getArguments().getOption(ProgramOptionConstants.HOST);
        Preconditions.checkArgument(host != null, "No hostname is provided");
        // Get the WorkflowProgramInfo if it is started by Workflow
        WorkflowProgramInfo workflowInfo = WorkflowProgramInfo.create(arguments);
        DatasetFramework programDatasetFramework = workflowInfo == null ? datasetFramework : NameMappedDatasetFramework.createFromWorkflowProgramInfo(datasetFramework, workflowInfo, appSpec);
        // Setup dataset framework context, if required
        if (programDatasetFramework instanceof ProgramContextAware) {
            ProgramId programId = program.getId();
            ((ProgramContextAware) programDatasetFramework).setContext(new BasicProgramContext(programId.run(runId)));
        }
        PluginInstantiator pluginInstantiator = createPluginInstantiator(options, program.getClassLoader());
        if (pluginInstantiator != null) {
            closeables.addFirst(pluginInstantiator);
        }
        SparkRuntimeContext runtimeContext = new SparkRuntimeContext(new Configuration(hConf), program, options, cConf, host, txClient, programDatasetFramework, metricsCollectionService, workflowInfo, pluginInstantiator, secureStore, secureStoreManager, accessEnforcer, authenticationContext, messagingService, serviceAnnouncer, pluginFinder, locationFactory, metadataReader, metadataPublisher, namespaceQueryAdmin, fieldLineageWriter, remoteClientFactory, () -> {
        });
        closeables.addFirst(runtimeContext);
        Spark spark;
        try {
            spark = new InstantiatorFactory(false).get(TypeToken.of(program.<Spark>getMainClass())).create();
        } catch (Exception e) {
            LOG.error("Failed to instantiate Spark class for {}", spec.getClassName(), e);
            throw Throwables.propagate(e);
        }
        boolean isLocal = SparkRuntimeContextConfig.isLocal(options);
        SparkSubmitter submitter;
        // If MasterEnvironment is not available, use non-master env spark submitters
        MasterEnvironment masterEnv = MasterEnvironments.getMasterEnvironment();
        if (masterEnv != null && cConf.getBoolean(Constants.Environment.PROGRAM_SUBMISSION_MASTER_ENV_ENABLED, true)) {
            submitter = new MasterEnvironmentSparkSubmitter(cConf, locationFactory, host, runtimeContext, masterEnv);
        } else {
            submitter = isLocal ? new LocalSparkSubmitter() : new DistributedSparkSubmitter(hConf, locationFactory, host, runtimeContext, options.getArguments().getOption(Constants.AppFabric.APP_SCHEDULER_QUEUE));
        }
        Service sparkRuntimeService = new SparkRuntimeService(cConf, spark, getPluginArchive(options), runtimeContext, submitter, locationFactory, isLocal, fieldLineageWriter, masterEnv);
        sparkRuntimeService.addListener(createRuntimeServiceListener(closeables), Threads.SAME_THREAD_EXECUTOR);
        ProgramController controller = new SparkProgramController(sparkRuntimeService, runtimeContext);
        LOG.debug("Starting Spark Job. Context: {}", runtimeContext);
        if (isLocal || UserGroupInformation.isSecurityEnabled()) {
            sparkRuntimeService.start();
        } else {
            ProgramRunners.startAsUser(cConf.get(Constants.CFG_HDFS_USER), sparkRuntimeService);
        }
        return controller;
    } catch (Throwable t) {
        closeAllQuietly(closeables);
        throw Throwables.propagate(t);
    }
}
Also used : ApplicationSpecification(io.cdap.cdap.api.app.ApplicationSpecification) MasterEnvironmentSparkSubmitter(io.cdap.cdap.app.runtime.spark.submit.MasterEnvironmentSparkSubmitter) MasterEnvironmentSparkSubmitter(io.cdap.cdap.app.runtime.spark.submit.MasterEnvironmentSparkSubmitter) LocalSparkSubmitter(io.cdap.cdap.app.runtime.spark.submit.LocalSparkSubmitter) SparkSubmitter(io.cdap.cdap.app.runtime.spark.submit.SparkSubmitter) DistributedSparkSubmitter(io.cdap.cdap.app.runtime.spark.submit.DistributedSparkSubmitter) Configuration(org.apache.hadoop.conf.Configuration) CConfiguration(io.cdap.cdap.common.conf.CConfiguration) Closeable(java.io.Closeable) DistributedSparkSubmitter(io.cdap.cdap.app.runtime.spark.submit.DistributedSparkSubmitter) DatasetFramework(io.cdap.cdap.data2.dataset2.DatasetFramework) NameMappedDatasetFramework(io.cdap.cdap.internal.app.runtime.workflow.NameMappedDatasetFramework) InstantiatorFactory(io.cdap.cdap.common.lang.InstantiatorFactory) SparkSpecification(io.cdap.cdap.api.spark.SparkSpecification) ProgramType(io.cdap.cdap.proto.ProgramType) RunId(org.apache.twill.api.RunId) ProgramController(io.cdap.cdap.app.runtime.ProgramController) Arguments(io.cdap.cdap.app.runtime.Arguments) MessagingService(io.cdap.cdap.messaging.MessagingService) Service(com.google.common.util.concurrent.Service) MetricsCollectionService(io.cdap.cdap.api.metrics.MetricsCollectionService) ProgramId(io.cdap.cdap.proto.id.ProgramId) BasicProgramContext(io.cdap.cdap.internal.app.runtime.BasicProgramContext) LinkedList(java.util.LinkedList) IOException(java.io.IOException) WorkflowProgramInfo(io.cdap.cdap.internal.app.runtime.workflow.WorkflowProgramInfo) MasterEnvironment(io.cdap.cdap.master.spi.environment.MasterEnvironment) PluginInstantiator(io.cdap.cdap.internal.app.runtime.plugin.PluginInstantiator) Spark(io.cdap.cdap.api.spark.Spark) LocalSparkSubmitter(io.cdap.cdap.app.runtime.spark.submit.LocalSparkSubmitter) ProgramContextAware(io.cdap.cdap.data.ProgramContextAware)

Example 7 with ProgramContextAware

use of io.cdap.cdap.data.ProgramContextAware in project cdap by cdapio.

the class ServiceProgramRunner method run.

@Override
public ProgramController run(Program program, ProgramOptions options) {
    int instanceId = Integer.parseInt(options.getArguments().getOption(ProgramOptionConstants.INSTANCE_ID, "-1"));
    Preconditions.checkArgument(instanceId >= 0, "Missing instance Id");
    int instanceCount = Integer.parseInt(options.getArguments().getOption(ProgramOptionConstants.INSTANCES, "0"));
    Preconditions.checkArgument(instanceCount > 0, "Invalid or missing instance count");
    RunId runId = ProgramRunners.getRunId(options);
    ApplicationSpecification appSpec = program.getApplicationSpecification();
    Preconditions.checkNotNull(appSpec, "Missing application specification.");
    ProgramType programType = program.getType();
    Preconditions.checkNotNull(programType, "Missing processor type.");
    Preconditions.checkArgument(programType == ProgramType.SERVICE, "Only Service process type is supported.");
    ServiceSpecification spec = appSpec.getServices().get(program.getName());
    String host = options.getArguments().getOption(ProgramOptionConstants.HOST);
    Preconditions.checkArgument(host != null, "No hostname is provided");
    // Setup dataset framework context, if required
    if (datasetFramework instanceof ProgramContextAware) {
        ProgramId programId = program.getId();
        ((ProgramContextAware) datasetFramework).setContext(new BasicProgramContext(programId.run(runId)));
    }
    final PluginInstantiator pluginInstantiator = createPluginInstantiator(options, program.getClassLoader());
    try {
        RetryStrategy retryStrategy = SystemArguments.getRetryStrategy(options.getUserArguments().asMap(), program.getType(), cConf);
        ArtifactManager artifactManager = artifactManagerFactory.create(program.getId().getNamespaceId(), retryStrategy);
        ServiceHttpServer component = new ServiceHttpServer(host, program, options, cConf, spec, instanceId, instanceCount, serviceAnnouncer, metricsCollectionService, datasetFramework, txClient, discoveryServiceClient, pluginInstantiator, secureStore, secureStoreManager, messagingService, artifactManager, metadataReader, metadataPublisher, namespaceQueryAdmin, pluginFinder, fieldLineageWriter, transactionRunner, preferencesFetcher, remoteClientFactory, contextAccessEnforcer);
        // Add a service listener to make sure the plugin instantiator is closed when the http server is finished.
        component.addListener(createRuntimeServiceListener(Collections.singleton(pluginInstantiator)), Threads.SAME_THREAD_EXECUTOR);
        ProgramController controller = new ServiceProgramControllerAdapter(component, program.getId().run(runId));
        component.start();
        return controller;
    } catch (Throwable t) {
        Closeables.closeQuietly(pluginInstantiator);
        throw t;
    }
}
Also used : ApplicationSpecification(io.cdap.cdap.api.app.ApplicationSpecification) ServiceSpecification(io.cdap.cdap.api.service.ServiceSpecification) ProgramController(io.cdap.cdap.app.runtime.ProgramController) ProgramId(io.cdap.cdap.proto.id.ProgramId) BasicProgramContext(io.cdap.cdap.internal.app.runtime.BasicProgramContext) ServiceHttpServer(io.cdap.cdap.internal.app.services.ServiceHttpServer) ArtifactManager(io.cdap.cdap.api.artifact.ArtifactManager) PluginInstantiator(io.cdap.cdap.internal.app.runtime.plugin.PluginInstantiator) ProgramType(io.cdap.cdap.proto.ProgramType) ProgramRunId(io.cdap.cdap.proto.id.ProgramRunId) RunId(org.apache.twill.api.RunId) ProgramContextAware(io.cdap.cdap.data.ProgramContextAware) RetryStrategy(io.cdap.cdap.common.service.RetryStrategy)

Example 8 with ProgramContextAware

use of io.cdap.cdap.data.ProgramContextAware in project cdap by cdapio.

the class WorkerProgramRunner method run.

@Override
public ProgramController run(Program program, ProgramOptions options) {
    ApplicationSpecification appSpec = program.getApplicationSpecification();
    Preconditions.checkNotNull(appSpec, "Missing application specification.");
    int instanceId = Integer.parseInt(options.getArguments().getOption(ProgramOptionConstants.INSTANCE_ID, "-1"));
    Preconditions.checkArgument(instanceId >= 0, "Missing instance Id");
    int instanceCount = Integer.parseInt(options.getArguments().getOption(ProgramOptionConstants.INSTANCES, "0"));
    Preconditions.checkArgument(instanceCount > 0, "Invalid or missing instance count");
    RunId runId = ProgramRunners.getRunId(options);
    ProgramType programType = program.getType();
    Preconditions.checkNotNull(programType, "Missing processor type.");
    Preconditions.checkArgument(programType == ProgramType.WORKER, "Only Worker process type is supported.");
    WorkerSpecification workerSpec = appSpec.getWorkers().get(program.getName());
    Preconditions.checkArgument(workerSpec != null, "Missing Worker specification for %s", program.getId());
    String instances = options.getArguments().getOption(ProgramOptionConstants.INSTANCES, String.valueOf(workerSpec.getInstances()));
    WorkerSpecification newWorkerSpec = new WorkerSpecification(workerSpec.getClassName(), workerSpec.getName(), workerSpec.getDescription(), workerSpec.getProperties(), workerSpec.getDatasets(), workerSpec.getResources(), Integer.parseInt(instances), workerSpec.getPlugins());
    // Setup dataset framework context, if required
    if (datasetFramework instanceof ProgramContextAware) {
        ProgramId programId = program.getId();
        ((ProgramContextAware) datasetFramework).setContext(new BasicProgramContext(programId.run(runId)));
    }
    final PluginInstantiator pluginInstantiator = createPluginInstantiator(options, program.getClassLoader());
    try {
        BasicWorkerContext context = new BasicWorkerContext(newWorkerSpec, program, options, cConf, instanceId, instanceCount, metricsCollectionService, datasetFramework, txClient, discoveryServiceClient, pluginInstantiator, secureStore, secureStoreManager, messagingService, metadataReader, metadataPublisher, namespaceQueryAdmin, fieldLineageWriter, remoteClientFactory);
        WorkerDriver worker = new WorkerDriver(program, newWorkerSpec, context);
        // Add a service listener to make sure the plugin instantiator is closed when the worker driver finished.
        worker.addListener(createRuntimeServiceListener(Collections.singleton(pluginInstantiator)), Threads.SAME_THREAD_EXECUTOR);
        ProgramController controller = new WorkerControllerServiceAdapter(worker, program.getId().run(runId));
        worker.start();
        return controller;
    } catch (Throwable t) {
        Closeables.closeQuietly(pluginInstantiator);
        throw t;
    }
}
Also used : ApplicationSpecification(io.cdap.cdap.api.app.ApplicationSpecification) ProgramController(io.cdap.cdap.app.runtime.ProgramController) WorkerSpecification(io.cdap.cdap.api.worker.WorkerSpecification) ProgramId(io.cdap.cdap.proto.id.ProgramId) BasicProgramContext(io.cdap.cdap.internal.app.runtime.BasicProgramContext) PluginInstantiator(io.cdap.cdap.internal.app.runtime.plugin.PluginInstantiator) ProgramType(io.cdap.cdap.proto.ProgramType) ProgramRunId(io.cdap.cdap.proto.id.ProgramRunId) RunId(org.apache.twill.api.RunId) ProgramContextAware(io.cdap.cdap.data.ProgramContextAware)

Example 9 with ProgramContextAware

use of io.cdap.cdap.data.ProgramContextAware in project cdap by cdapio.

the class WorkflowProgramRunner method run.

@Override
public ProgramController run(final Program program, final ProgramOptions options) {
    // Extract and verify options
    ApplicationSpecification appSpec = program.getApplicationSpecification();
    Preconditions.checkNotNull(appSpec, "Missing application specification.");
    ProgramType processorType = program.getType();
    Preconditions.checkNotNull(processorType, "Missing processor type.");
    Preconditions.checkArgument(processorType == ProgramType.WORKFLOW, "Only WORKFLOW process type is supported.");
    WorkflowSpecification workflowSpec = appSpec.getWorkflows().get(program.getName());
    Preconditions.checkNotNull(workflowSpec, "Missing WorkflowSpecification for %s", program.getName());
    final RunId runId = ProgramRunners.getRunId(options);
    // Setup dataset framework context, if required
    if (datasetFramework instanceof ProgramContextAware) {
        ProgramId programId = program.getId();
        ((ProgramContextAware) datasetFramework).setContext(new BasicProgramContext(programId.run(runId)));
    }
    // List of all Closeable resources that needs to be cleanup
    final List<Closeable> closeables = new ArrayList<>();
    try {
        PluginInstantiator pluginInstantiator = createPluginInstantiator(options, program.getClassLoader());
        if (pluginInstantiator != null) {
            closeables.add(pluginInstantiator);
        }
        WorkflowDriver driver = new WorkflowDriver(program, options, workflowSpec, programRunnerFactory, metricsCollectionService, datasetFramework, discoveryServiceClient, txClient, workflowStateWriter, cConf, pluginInstantiator, secureStore, secureStoreManager, messagingService, programStateWriter, metadataReader, metadataPublisher, fieldLineageWriter, namespaceQueryAdmin, remoteClientFactory);
        // Controller needs to be created before starting the driver so that the state change of the driver
        // service can be fully captured by the controller.
        ProgramController controller = new WorkflowProgramController(program.getId().run(runId), driver);
        driver.start();
        return controller;
    } catch (Exception e) {
        closeAllQuietly(closeables);
        throw Throwables.propagate(e);
    }
}
Also used : ApplicationSpecification(io.cdap.cdap.api.app.ApplicationSpecification) ProgramController(io.cdap.cdap.app.runtime.ProgramController) Closeable(java.io.Closeable) ArrayList(java.util.ArrayList) ProgramId(io.cdap.cdap.proto.id.ProgramId) BasicProgramContext(io.cdap.cdap.internal.app.runtime.BasicProgramContext) WorkflowSpecification(io.cdap.cdap.api.workflow.WorkflowSpecification) PluginInstantiator(io.cdap.cdap.internal.app.runtime.plugin.PluginInstantiator) ProgramType(io.cdap.cdap.proto.ProgramType) RunId(org.apache.twill.api.RunId) ProgramContextAware(io.cdap.cdap.data.ProgramContextAware)

Example 10 with ProgramContextAware

use of io.cdap.cdap.data.ProgramContextAware in project cdap by caskdata.

the class WorkerProgramRunner method run.

@Override
public ProgramController run(Program program, ProgramOptions options) {
    ApplicationSpecification appSpec = program.getApplicationSpecification();
    Preconditions.checkNotNull(appSpec, "Missing application specification.");
    int instanceId = Integer.parseInt(options.getArguments().getOption(ProgramOptionConstants.INSTANCE_ID, "-1"));
    Preconditions.checkArgument(instanceId >= 0, "Missing instance Id");
    int instanceCount = Integer.parseInt(options.getArguments().getOption(ProgramOptionConstants.INSTANCES, "0"));
    Preconditions.checkArgument(instanceCount > 0, "Invalid or missing instance count");
    RunId runId = ProgramRunners.getRunId(options);
    ProgramType programType = program.getType();
    Preconditions.checkNotNull(programType, "Missing processor type.");
    Preconditions.checkArgument(programType == ProgramType.WORKER, "Only Worker process type is supported.");
    WorkerSpecification workerSpec = appSpec.getWorkers().get(program.getName());
    Preconditions.checkArgument(workerSpec != null, "Missing Worker specification for %s", program.getId());
    String instances = options.getArguments().getOption(ProgramOptionConstants.INSTANCES, String.valueOf(workerSpec.getInstances()));
    WorkerSpecification newWorkerSpec = new WorkerSpecification(workerSpec.getClassName(), workerSpec.getName(), workerSpec.getDescription(), workerSpec.getProperties(), workerSpec.getDatasets(), workerSpec.getResources(), Integer.parseInt(instances), workerSpec.getPlugins());
    // Setup dataset framework context, if required
    if (datasetFramework instanceof ProgramContextAware) {
        ProgramId programId = program.getId();
        ((ProgramContextAware) datasetFramework).setContext(new BasicProgramContext(programId.run(runId)));
    }
    final PluginInstantiator pluginInstantiator = createPluginInstantiator(options, program.getClassLoader());
    try {
        BasicWorkerContext context = new BasicWorkerContext(newWorkerSpec, program, options, cConf, instanceId, instanceCount, metricsCollectionService, datasetFramework, txClient, discoveryServiceClient, pluginInstantiator, secureStore, secureStoreManager, messagingService, metadataReader, metadataPublisher, namespaceQueryAdmin, fieldLineageWriter, remoteClientFactory);
        WorkerDriver worker = new WorkerDriver(program, newWorkerSpec, context);
        // Add a service listener to make sure the plugin instantiator is closed when the worker driver finished.
        worker.addListener(createRuntimeServiceListener(Collections.singleton(pluginInstantiator)), Threads.SAME_THREAD_EXECUTOR);
        ProgramController controller = new WorkerControllerServiceAdapter(worker, program.getId().run(runId));
        worker.start();
        return controller;
    } catch (Throwable t) {
        Closeables.closeQuietly(pluginInstantiator);
        throw t;
    }
}
Also used : ApplicationSpecification(io.cdap.cdap.api.app.ApplicationSpecification) ProgramController(io.cdap.cdap.app.runtime.ProgramController) WorkerSpecification(io.cdap.cdap.api.worker.WorkerSpecification) ProgramId(io.cdap.cdap.proto.id.ProgramId) BasicProgramContext(io.cdap.cdap.internal.app.runtime.BasicProgramContext) PluginInstantiator(io.cdap.cdap.internal.app.runtime.plugin.PluginInstantiator) ProgramType(io.cdap.cdap.proto.ProgramType) ProgramRunId(io.cdap.cdap.proto.id.ProgramRunId) RunId(org.apache.twill.api.RunId) ProgramContextAware(io.cdap.cdap.data.ProgramContextAware)

Aggregations

ProgramContextAware (io.cdap.cdap.data.ProgramContextAware)14 BasicProgramContext (io.cdap.cdap.internal.app.runtime.BasicProgramContext)14 PluginInstantiator (io.cdap.cdap.internal.app.runtime.plugin.PluginInstantiator)12 ApplicationSpecification (io.cdap.cdap.api.app.ApplicationSpecification)10 ProgramController (io.cdap.cdap.app.runtime.ProgramController)10 ProgramType (io.cdap.cdap.proto.ProgramType)10 ProgramId (io.cdap.cdap.proto.id.ProgramId)10 RunId (org.apache.twill.api.RunId)10 MetricsCollectionService (io.cdap.cdap.api.metrics.MetricsCollectionService)8 CConfiguration (io.cdap.cdap.common.conf.CConfiguration)8 DatasetFramework (io.cdap.cdap.data2.dataset2.DatasetFramework)8 NameMappedDatasetFramework (io.cdap.cdap.internal.app.runtime.workflow.NameMappedDatasetFramework)8 WorkflowProgramInfo (io.cdap.cdap.internal.app.runtime.workflow.WorkflowProgramInfo)8 MessagingService (io.cdap.cdap.messaging.MessagingService)8 ProgramRunId (io.cdap.cdap.proto.id.ProgramRunId)8 Closeable (java.io.Closeable)8 Service (com.google.common.util.concurrent.Service)6 Configuration (org.apache.hadoop.conf.Configuration)6 MapReduceSpecification (io.cdap.cdap.api.mapreduce.MapReduceSpecification)4 ClusterMode (io.cdap.cdap.app.guice.ClusterMode)4