Search in sources :

Example 1 with BroadcastVariableManager

use of org.apache.flink.runtime.broadcast.BroadcastVariableManager in project flink by apache.

the class TaskManagerServices method fromConfiguration.

// --------------------------------------------------------------------------------------------
//  Static factory methods for task manager services
// --------------------------------------------------------------------------------------------
/**
	 * Creates and returns the task manager services.
	 *
	 * @param resourceID resource ID of the task manager
	 * @param taskManagerServicesConfiguration task manager configuration
	 * @return task manager components
	 * @throws Exception
	 */
public static TaskManagerServices fromConfiguration(TaskManagerServicesConfiguration taskManagerServicesConfiguration, ResourceID resourceID) throws Exception {
    // pre-start checks
    checkTempDirs(taskManagerServicesConfiguration.getTmpDirPaths());
    final NetworkEnvironment network = createNetworkEnvironment(taskManagerServicesConfiguration);
    network.start();
    final TaskManagerLocation taskManagerLocation = new TaskManagerLocation(resourceID, taskManagerServicesConfiguration.getTaskManagerAddress(), network.getConnectionManager().getDataPort());
    // this call has to happen strictly after the network stack has been initialized
    final MemoryManager memoryManager = createMemoryManager(taskManagerServicesConfiguration);
    // start the I/O manager, it will create some temp directories.
    final IOManager ioManager = new IOManagerAsync(taskManagerServicesConfiguration.getTmpDirPaths());
    final MetricRegistry metricRegistry = new MetricRegistry(taskManagerServicesConfiguration.getMetricRegistryConfiguration());
    final TaskManagerMetricGroup taskManagerMetricGroup = new TaskManagerMetricGroup(metricRegistry, taskManagerLocation.getHostname(), taskManagerLocation.getResourceID().toString());
    // Initialize the TM metrics
    TaskExecutorMetricsInitializer.instantiateStatusMetrics(taskManagerMetricGroup, network);
    final BroadcastVariableManager broadcastVariableManager = new BroadcastVariableManager();
    final FileCache fileCache = new FileCache(taskManagerServicesConfiguration.getTmpDirPaths());
    final List<ResourceProfile> resourceProfiles = new ArrayList<>(taskManagerServicesConfiguration.getNumberOfSlots());
    for (int i = 0; i < taskManagerServicesConfiguration.getNumberOfSlots(); i++) {
        resourceProfiles.add(new ResourceProfile(1.0, 42));
    }
    final TimerService<AllocationID> timerService = new TimerService<>(new ScheduledThreadPoolExecutor(1), taskManagerServicesConfiguration.getTimerServiceShutdownTimeout());
    final TaskSlotTable taskSlotTable = new TaskSlotTable(resourceProfiles, timerService);
    final JobManagerTable jobManagerTable = new JobManagerTable();
    final JobLeaderService jobLeaderService = new JobLeaderService(taskManagerLocation);
    return new TaskManagerServices(taskManagerLocation, memoryManager, ioManager, network, metricRegistry, taskManagerMetricGroup, broadcastVariableManager, fileCache, taskSlotTable, jobManagerTable, jobLeaderService);
}
Also used : ResourceProfile(org.apache.flink.runtime.clusterframework.types.ResourceProfile) IOManager(org.apache.flink.runtime.io.disk.iomanager.IOManager) TaskManagerLocation(org.apache.flink.runtime.taskmanager.TaskManagerLocation) ScheduledThreadPoolExecutor(java.util.concurrent.ScheduledThreadPoolExecutor) MetricRegistry(org.apache.flink.runtime.metrics.MetricRegistry) TaskManagerMetricGroup(org.apache.flink.runtime.metrics.groups.TaskManagerMetricGroup) AllocationID(org.apache.flink.runtime.clusterframework.types.AllocationID) ArrayList(java.util.ArrayList) MemoryManager(org.apache.flink.runtime.memory.MemoryManager) TimerService(org.apache.flink.runtime.taskexecutor.slot.TimerService) FileCache(org.apache.flink.runtime.filecache.FileCache) IOManagerAsync(org.apache.flink.runtime.io.disk.iomanager.IOManagerAsync) TaskSlotTable(org.apache.flink.runtime.taskexecutor.slot.TaskSlotTable) BroadcastVariableManager(org.apache.flink.runtime.broadcast.BroadcastVariableManager) NetworkEnvironment(org.apache.flink.runtime.io.network.NetworkEnvironment)

Example 2 with BroadcastVariableManager

use of org.apache.flink.runtime.broadcast.BroadcastVariableManager in project flink by apache.

the class TaskExecutorITCase method testSlotAllocation.

@Test
public void testSlotAllocation() throws Exception {
    TestingFatalErrorHandler testingFatalErrorHandler = new TestingFatalErrorHandler();
    TestingHighAvailabilityServices testingHAServices = new TestingHighAvailabilityServices();
    final Configuration configuration = new Configuration();
    final ScheduledExecutorService scheduledExecutorService = new ScheduledThreadPoolExecutor(1);
    final ResourceID taskManagerResourceId = new ResourceID("foobar");
    final UUID rmLeaderId = UUID.randomUUID();
    final TestingLeaderElectionService rmLeaderElectionService = new TestingLeaderElectionService();
    final TestingLeaderRetrievalService rmLeaderRetrievalService = new TestingLeaderRetrievalService();
    final String rmAddress = "rm";
    final String jmAddress = "jm";
    final UUID jmLeaderId = UUID.randomUUID();
    final JobID jobId = new JobID();
    final ResourceProfile resourceProfile = new ResourceProfile(1.0, 1);
    testingHAServices.setResourceManagerLeaderElectionService(rmLeaderElectionService);
    testingHAServices.setResourceManagerLeaderRetriever(rmLeaderRetrievalService);
    testingHAServices.setJobMasterLeaderRetriever(jobId, new TestingLeaderRetrievalService(jmAddress, jmLeaderId));
    TestingSerialRpcService rpcService = new TestingSerialRpcService();
    ResourceManagerConfiguration resourceManagerConfiguration = new ResourceManagerConfiguration(Time.milliseconds(500L), Time.milliseconds(500L), Time.minutes(5L));
    SlotManagerFactory slotManagerFactory = new DefaultSlotManager.Factory();
    JobLeaderIdService jobLeaderIdService = new JobLeaderIdService(testingHAServices, rpcService.getScheduledExecutor(), resourceManagerConfiguration.getJobTimeout());
    MetricRegistry metricRegistry = mock(MetricRegistry.class);
    HeartbeatServices heartbeatServices = mock(HeartbeatServices.class, RETURNS_MOCKS);
    final TaskManagerConfiguration taskManagerConfiguration = TaskManagerConfiguration.fromConfiguration(configuration);
    final TaskManagerLocation taskManagerLocation = new TaskManagerLocation(taskManagerResourceId, InetAddress.getLocalHost(), 1234);
    final MemoryManager memoryManager = mock(MemoryManager.class);
    final IOManager ioManager = mock(IOManager.class);
    final NetworkEnvironment networkEnvironment = mock(NetworkEnvironment.class);
    final TaskManagerMetricGroup taskManagerMetricGroup = mock(TaskManagerMetricGroup.class);
    final BroadcastVariableManager broadcastVariableManager = mock(BroadcastVariableManager.class);
    final FileCache fileCache = mock(FileCache.class);
    final TaskSlotTable taskSlotTable = new TaskSlotTable(Arrays.asList(resourceProfile), new TimerService<AllocationID>(scheduledExecutorService, 100L));
    final JobManagerTable jobManagerTable = new JobManagerTable();
    final JobLeaderService jobLeaderService = new JobLeaderService(taskManagerLocation);
    ResourceManager<ResourceID> resourceManager = new StandaloneResourceManager(rpcService, resourceManagerConfiguration, testingHAServices, slotManagerFactory, metricRegistry, jobLeaderIdService, testingFatalErrorHandler);
    TaskExecutor taskExecutor = new TaskExecutor(taskManagerConfiguration, taskManagerLocation, rpcService, memoryManager, ioManager, networkEnvironment, testingHAServices, heartbeatServices, metricRegistry, taskManagerMetricGroup, broadcastVariableManager, fileCache, taskSlotTable, jobManagerTable, jobLeaderService, testingFatalErrorHandler);
    JobMasterGateway jmGateway = mock(JobMasterGateway.class);
    when(jmGateway.registerTaskManager(any(String.class), any(TaskManagerLocation.class), eq(jmLeaderId), any(Time.class))).thenReturn(FlinkCompletableFuture.<RegistrationResponse>completed(new JMTMRegistrationSuccess(taskManagerResourceId, 1234)));
    when(jmGateway.getHostname()).thenReturn(jmAddress);
    rpcService.registerGateway(rmAddress, resourceManager.getSelf());
    rpcService.registerGateway(jmAddress, jmGateway);
    final AllocationID allocationId = new AllocationID();
    final SlotRequest slotRequest = new SlotRequest(jobId, allocationId, resourceProfile);
    final SlotOffer slotOffer = new SlotOffer(allocationId, 0, resourceProfile);
    try {
        resourceManager.start();
        taskExecutor.start();
        // notify the RM that it is the leader
        rmLeaderElectionService.isLeader(rmLeaderId);
        // notify the TM about the new RM leader
        rmLeaderRetrievalService.notifyListener(rmAddress, rmLeaderId);
        Future<RegistrationResponse> registrationResponseFuture = resourceManager.registerJobManager(rmLeaderId, jmLeaderId, jmAddress, jobId);
        RegistrationResponse registrationResponse = registrationResponseFuture.get();
        assertTrue(registrationResponse instanceof JobMasterRegistrationSuccess);
        resourceManager.requestSlot(jmLeaderId, rmLeaderId, slotRequest);
        verify(jmGateway).offerSlots(eq(taskManagerResourceId), (Iterable<SlotOffer>) argThat(Matchers.contains(slotOffer)), eq(jmLeaderId), any(Time.class));
    } finally {
        if (testingFatalErrorHandler.hasExceptionOccurred()) {
            testingFatalErrorHandler.rethrowError();
        }
    }
}
Also used : ResourceManagerConfiguration(org.apache.flink.runtime.resourcemanager.ResourceManagerConfiguration) Configuration(org.apache.flink.configuration.Configuration) TestingLeaderRetrievalService(org.apache.flink.runtime.leaderelection.TestingLeaderRetrievalService) ScheduledThreadPoolExecutor(java.util.concurrent.ScheduledThreadPoolExecutor) JobLeaderIdService(org.apache.flink.runtime.resourcemanager.JobLeaderIdService) SlotManagerFactory(org.apache.flink.runtime.resourcemanager.slotmanager.SlotManagerFactory) Time(org.apache.flink.api.common.time.Time) StandaloneResourceManager(org.apache.flink.runtime.resourcemanager.StandaloneResourceManager) JobMasterGateway(org.apache.flink.runtime.jobmaster.JobMasterGateway) SlotRequest(org.apache.flink.runtime.resourcemanager.SlotRequest) TestingHighAvailabilityServices(org.apache.flink.runtime.highavailability.TestingHighAvailabilityServices) ResourceID(org.apache.flink.runtime.clusterframework.types.ResourceID) BroadcastVariableManager(org.apache.flink.runtime.broadcast.BroadcastVariableManager) TestingSerialRpcService(org.apache.flink.runtime.rpc.TestingSerialRpcService) UUID(java.util.UUID) RegistrationResponse(org.apache.flink.runtime.registration.RegistrationResponse) TestingFatalErrorHandler(org.apache.flink.runtime.util.TestingFatalErrorHandler) HeartbeatServices(org.apache.flink.runtime.heartbeat.HeartbeatServices) ResourceProfile(org.apache.flink.runtime.clusterframework.types.ResourceProfile) JMTMRegistrationSuccess(org.apache.flink.runtime.jobmaster.JMTMRegistrationSuccess) ScheduledExecutorService(java.util.concurrent.ScheduledExecutorService) TestingLeaderElectionService(org.apache.flink.runtime.leaderelection.TestingLeaderElectionService) SlotOffer(org.apache.flink.runtime.taskexecutor.slot.SlotOffer) JobMasterRegistrationSuccess(org.apache.flink.runtime.jobmaster.JobMasterRegistrationSuccess) IOManager(org.apache.flink.runtime.io.disk.iomanager.IOManager) TaskManagerLocation(org.apache.flink.runtime.taskmanager.TaskManagerLocation) MetricRegistry(org.apache.flink.runtime.metrics.MetricRegistry) TaskManagerMetricGroup(org.apache.flink.runtime.metrics.groups.TaskManagerMetricGroup) AllocationID(org.apache.flink.runtime.clusterframework.types.AllocationID) ResourceManagerConfiguration(org.apache.flink.runtime.resourcemanager.ResourceManagerConfiguration) MemoryManager(org.apache.flink.runtime.memory.MemoryManager) FileCache(org.apache.flink.runtime.filecache.FileCache) SlotManagerFactory(org.apache.flink.runtime.resourcemanager.slotmanager.SlotManagerFactory) TaskSlotTable(org.apache.flink.runtime.taskexecutor.slot.TaskSlotTable) NetworkEnvironment(org.apache.flink.runtime.io.network.NetworkEnvironment) JobID(org.apache.flink.api.common.JobID) Test(org.junit.Test)

Aggregations

ScheduledThreadPoolExecutor (java.util.concurrent.ScheduledThreadPoolExecutor)2 BroadcastVariableManager (org.apache.flink.runtime.broadcast.BroadcastVariableManager)2 AllocationID (org.apache.flink.runtime.clusterframework.types.AllocationID)2 ResourceProfile (org.apache.flink.runtime.clusterframework.types.ResourceProfile)2 FileCache (org.apache.flink.runtime.filecache.FileCache)2 IOManager (org.apache.flink.runtime.io.disk.iomanager.IOManager)2 NetworkEnvironment (org.apache.flink.runtime.io.network.NetworkEnvironment)2 MemoryManager (org.apache.flink.runtime.memory.MemoryManager)2 MetricRegistry (org.apache.flink.runtime.metrics.MetricRegistry)2 TaskManagerMetricGroup (org.apache.flink.runtime.metrics.groups.TaskManagerMetricGroup)2 TaskSlotTable (org.apache.flink.runtime.taskexecutor.slot.TaskSlotTable)2 TaskManagerLocation (org.apache.flink.runtime.taskmanager.TaskManagerLocation)2 ArrayList (java.util.ArrayList)1 UUID (java.util.UUID)1 ScheduledExecutorService (java.util.concurrent.ScheduledExecutorService)1 JobID (org.apache.flink.api.common.JobID)1 Time (org.apache.flink.api.common.time.Time)1 Configuration (org.apache.flink.configuration.Configuration)1 ResourceID (org.apache.flink.runtime.clusterframework.types.ResourceID)1 HeartbeatServices (org.apache.flink.runtime.heartbeat.HeartbeatServices)1