Search in sources :

Example 1 with RpcGatewayRetriever

use of org.apache.flink.runtime.webmonitor.retriever.impl.RpcGatewayRetriever in project flink by apache.

the class DefaultDispatcherResourceManagerComponentFactory method create.

@Override
public DispatcherResourceManagerComponent create(Configuration configuration, ResourceID resourceId, Executor ioExecutor, RpcService rpcService, HighAvailabilityServices highAvailabilityServices, BlobServer blobServer, HeartbeatServices heartbeatServices, MetricRegistry metricRegistry, ExecutionGraphInfoStore executionGraphInfoStore, MetricQueryServiceRetriever metricQueryServiceRetriever, FatalErrorHandler fatalErrorHandler) throws Exception {
    LeaderRetrievalService dispatcherLeaderRetrievalService = null;
    LeaderRetrievalService resourceManagerRetrievalService = null;
    WebMonitorEndpoint<?> webMonitorEndpoint = null;
    ResourceManagerService resourceManagerService = null;
    DispatcherRunner dispatcherRunner = null;
    try {
        dispatcherLeaderRetrievalService = highAvailabilityServices.getDispatcherLeaderRetriever();
        resourceManagerRetrievalService = highAvailabilityServices.getResourceManagerLeaderRetriever();
        final LeaderGatewayRetriever<DispatcherGateway> dispatcherGatewayRetriever = new RpcGatewayRetriever<>(rpcService, DispatcherGateway.class, DispatcherId::fromUuid, new ExponentialBackoffRetryStrategy(12, Duration.ofMillis(10), Duration.ofMillis(50)));
        final LeaderGatewayRetriever<ResourceManagerGateway> resourceManagerGatewayRetriever = new RpcGatewayRetriever<>(rpcService, ResourceManagerGateway.class, ResourceManagerId::fromUuid, new ExponentialBackoffRetryStrategy(12, Duration.ofMillis(10), Duration.ofMillis(50)));
        final ScheduledExecutorService executor = WebMonitorEndpoint.createExecutorService(configuration.getInteger(RestOptions.SERVER_NUM_THREADS), configuration.getInteger(RestOptions.SERVER_THREAD_PRIORITY), "DispatcherRestEndpoint");
        final long updateInterval = configuration.getLong(MetricOptions.METRIC_FETCHER_UPDATE_INTERVAL);
        final MetricFetcher metricFetcher = updateInterval == 0 ? VoidMetricFetcher.INSTANCE : MetricFetcherImpl.fromConfiguration(configuration, metricQueryServiceRetriever, dispatcherGatewayRetriever, executor);
        webMonitorEndpoint = restEndpointFactory.createRestEndpoint(configuration, dispatcherGatewayRetriever, resourceManagerGatewayRetriever, blobServer, executor, metricFetcher, highAvailabilityServices.getClusterRestEndpointLeaderElectionService(), fatalErrorHandler);
        log.debug("Starting Dispatcher REST endpoint.");
        webMonitorEndpoint.start();
        final String hostname = RpcUtils.getHostname(rpcService);
        resourceManagerService = ResourceManagerServiceImpl.create(resourceManagerFactory, configuration, resourceId, rpcService, highAvailabilityServices, heartbeatServices, fatalErrorHandler, new ClusterInformation(hostname, blobServer.getPort()), webMonitorEndpoint.getRestBaseUrl(), metricRegistry, hostname, ioExecutor);
        final HistoryServerArchivist historyServerArchivist = HistoryServerArchivist.createHistoryServerArchivist(configuration, webMonitorEndpoint, ioExecutor);
        final DispatcherOperationCaches dispatcherOperationCaches = new DispatcherOperationCaches(configuration.get(RestOptions.ASYNC_OPERATION_STORE_DURATION));
        final PartialDispatcherServices partialDispatcherServices = new PartialDispatcherServices(configuration, highAvailabilityServices, resourceManagerGatewayRetriever, blobServer, heartbeatServices, () -> JobManagerMetricGroup.createJobManagerMetricGroup(metricRegistry, hostname), executionGraphInfoStore, fatalErrorHandler, historyServerArchivist, metricRegistry.getMetricQueryServiceGatewayRpcAddress(), ioExecutor, dispatcherOperationCaches);
        log.debug("Starting Dispatcher.");
        dispatcherRunner = dispatcherRunnerFactory.createDispatcherRunner(highAvailabilityServices.getDispatcherLeaderElectionService(), fatalErrorHandler, new HaServicesJobPersistenceComponentFactory(highAvailabilityServices), ioExecutor, rpcService, partialDispatcherServices);
        log.debug("Starting ResourceManagerService.");
        resourceManagerService.start();
        resourceManagerRetrievalService.start(resourceManagerGatewayRetriever);
        dispatcherLeaderRetrievalService.start(dispatcherGatewayRetriever);
        return new DispatcherResourceManagerComponent(dispatcherRunner, resourceManagerService, dispatcherLeaderRetrievalService, resourceManagerRetrievalService, webMonitorEndpoint, fatalErrorHandler, dispatcherOperationCaches);
    } catch (Exception exception) {
        // clean up all started components
        if (dispatcherLeaderRetrievalService != null) {
            try {
                dispatcherLeaderRetrievalService.stop();
            } catch (Exception e) {
                exception = ExceptionUtils.firstOrSuppressed(e, exception);
            }
        }
        if (resourceManagerRetrievalService != null) {
            try {
                resourceManagerRetrievalService.stop();
            } catch (Exception e) {
                exception = ExceptionUtils.firstOrSuppressed(e, exception);
            }
        }
        final Collection<CompletableFuture<Void>> terminationFutures = new ArrayList<>(3);
        if (webMonitorEndpoint != null) {
            terminationFutures.add(webMonitorEndpoint.closeAsync());
        }
        if (resourceManagerService != null) {
            terminationFutures.add(resourceManagerService.closeAsync());
        }
        if (dispatcherRunner != null) {
            terminationFutures.add(dispatcherRunner.closeAsync());
        }
        final FutureUtils.ConjunctFuture<Void> terminationFuture = FutureUtils.completeAll(terminationFutures);
        try {
            terminationFuture.get();
        } catch (Exception e) {
            exception = ExceptionUtils.firstOrSuppressed(e, exception);
        }
        throw new FlinkException("Could not create the DispatcherResourceManagerComponent.", exception);
    }
}
Also used : ExponentialBackoffRetryStrategy(org.apache.flink.util.concurrent.ExponentialBackoffRetryStrategy) DispatcherGateway(org.apache.flink.runtime.dispatcher.DispatcherGateway) ResourceManagerGateway(org.apache.flink.runtime.resourcemanager.ResourceManagerGateway) RpcGatewayRetriever(org.apache.flink.runtime.webmonitor.retriever.impl.RpcGatewayRetriever) DispatcherRunner(org.apache.flink.runtime.dispatcher.runner.DispatcherRunner) DispatcherOperationCaches(org.apache.flink.runtime.dispatcher.DispatcherOperationCaches) ResourceManagerId(org.apache.flink.runtime.resourcemanager.ResourceManagerId) HistoryServerArchivist(org.apache.flink.runtime.dispatcher.HistoryServerArchivist) HaServicesJobPersistenceComponentFactory(org.apache.flink.runtime.jobmanager.HaServicesJobPersistenceComponentFactory) ScheduledExecutorService(java.util.concurrent.ScheduledExecutorService) PartialDispatcherServices(org.apache.flink.runtime.dispatcher.PartialDispatcherServices) ResourceManagerService(org.apache.flink.runtime.resourcemanager.ResourceManagerService) DispatcherId(org.apache.flink.runtime.dispatcher.DispatcherId) ClusterInformation(org.apache.flink.runtime.entrypoint.ClusterInformation) VoidMetricFetcher(org.apache.flink.runtime.rest.handler.legacy.metrics.VoidMetricFetcher) MetricFetcher(org.apache.flink.runtime.rest.handler.legacy.metrics.MetricFetcher) FlinkException(org.apache.flink.util.FlinkException) FlinkException(org.apache.flink.util.FlinkException) LeaderRetrievalService(org.apache.flink.runtime.leaderretrieval.LeaderRetrievalService) Collection(java.util.Collection)

Aggregations

Collection (java.util.Collection)1 ScheduledExecutorService (java.util.concurrent.ScheduledExecutorService)1 DispatcherGateway (org.apache.flink.runtime.dispatcher.DispatcherGateway)1 DispatcherId (org.apache.flink.runtime.dispatcher.DispatcherId)1 DispatcherOperationCaches (org.apache.flink.runtime.dispatcher.DispatcherOperationCaches)1 HistoryServerArchivist (org.apache.flink.runtime.dispatcher.HistoryServerArchivist)1 PartialDispatcherServices (org.apache.flink.runtime.dispatcher.PartialDispatcherServices)1 DispatcherRunner (org.apache.flink.runtime.dispatcher.runner.DispatcherRunner)1 ClusterInformation (org.apache.flink.runtime.entrypoint.ClusterInformation)1 HaServicesJobPersistenceComponentFactory (org.apache.flink.runtime.jobmanager.HaServicesJobPersistenceComponentFactory)1 LeaderRetrievalService (org.apache.flink.runtime.leaderretrieval.LeaderRetrievalService)1 ResourceManagerGateway (org.apache.flink.runtime.resourcemanager.ResourceManagerGateway)1 ResourceManagerId (org.apache.flink.runtime.resourcemanager.ResourceManagerId)1 ResourceManagerService (org.apache.flink.runtime.resourcemanager.ResourceManagerService)1 MetricFetcher (org.apache.flink.runtime.rest.handler.legacy.metrics.MetricFetcher)1 VoidMetricFetcher (org.apache.flink.runtime.rest.handler.legacy.metrics.VoidMetricFetcher)1 RpcGatewayRetriever (org.apache.flink.runtime.webmonitor.retriever.impl.RpcGatewayRetriever)1 FlinkException (org.apache.flink.util.FlinkException)1 ExponentialBackoffRetryStrategy (org.apache.flink.util.concurrent.ExponentialBackoffRetryStrategy)1