Examples with SegmentHandoffNotifier org.apache.druid.segment.handoff.SegmentHandoffNotifier used on opensource projects

Example 1 with SegmentHandoffNotifier

use of org.apache.druid.segment.handoff.SegmentHandoffNotifier in project druid by druid-io.

the class AppenderatorDriverRealtimeIndexTaskTest method makeToolboxFactory.

private void makeToolboxFactory(final File directory) {
    taskStorage = new HeapMemoryTaskStorage(new TaskStorageConfig(null));
    publishedSegments = new CopyOnWriteArrayList<>();
    ObjectMapper mapper = new DefaultObjectMapper();
    mapper.registerSubtypes(LinearShardSpec.class);
    mapper.registerSubtypes(NumberedShardSpec.class);
    IndexerSQLMetadataStorageCoordinator mdc = new IndexerSQLMetadataStorageCoordinator(mapper, derbyConnectorRule.metadataTablesConfigSupplier().get(), derbyConnectorRule.getConnector()) {

        @Override
        public Set<DataSegment> announceHistoricalSegments(Set<DataSegment> segments) throws IOException {
            Set<DataSegment> result = super.announceHistoricalSegments(segments);
            Assert.assertFalse("Segment latch not initialized, did you forget to call expectPublishSegments?", segmentLatch == null);
            publishedSegments.addAll(result);
            segments.forEach(s -> segmentLatch.countDown());
            return result;
        }

        @Override
        public SegmentPublishResult announceHistoricalSegments(Set<DataSegment> segments, Set<DataSegment> segmentsToDrop, DataSourceMetadata startMetadata, DataSourceMetadata endMetadata) throws IOException {
            SegmentPublishResult result = super.announceHistoricalSegments(segments, segmentsToDrop, startMetadata, endMetadata);
            Assert.assertFalse("Segment latch not initialized, did you forget to call expectPublishSegments?", segmentLatch == null);
            publishedSegments.addAll(result.getSegments());
            result.getSegments().forEach(s -> segmentLatch.countDown());
            return result;
        }
    };
    taskLockbox = new TaskLockbox(taskStorage, mdc);
    final TaskConfig taskConfig = new TaskConfig(directory.getPath(), null, null, 50000, null, true, null, null, null, false, false, TaskConfig.BATCH_PROCESSING_MODE_DEFAULT.name());
    final TaskActionToolbox taskActionToolbox = new TaskActionToolbox(taskLockbox, taskStorage, mdc, EMITTER, EasyMock.createMock(SupervisorManager.class));
    final TaskActionClientFactory taskActionClientFactory = new LocalTaskActionClientFactory(taskStorage, taskActionToolbox, new TaskAuditLogConfig(false));
    final QueryRunnerFactoryConglomerate conglomerate = new DefaultQueryRunnerFactoryConglomerate(ImmutableMap.of(TimeseriesQuery.class, new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(), new TimeseriesQueryEngine(), (query, future) -> {
    // do nothing
    })));
    handOffCallbacks = new ConcurrentHashMap<>();
    final SegmentHandoffNotifierFactory handoffNotifierFactory = dataSource -> new SegmentHandoffNotifier() {

        @Override
        public boolean registerSegmentHandoffCallback(SegmentDescriptor descriptor, Executor exec, Runnable handOffRunnable) {
            handOffCallbacks.put(descriptor, new Pair<>(exec, handOffRunnable));
            handoffLatch.countDown();
            return true;
        }

        @Override
        public void start() {
        // Noop
        }

        @Override
        public void close() {
        // Noop
        }
    };
    final TestUtils testUtils = new TestUtils();
    taskToolboxFactory = new TaskToolboxFactory(taskConfig, new DruidNode("druid/middlemanager", "localhost", false, 8091, null, true, false), taskActionClientFactory, EMITTER, new TestDataSegmentPusher(), new TestDataSegmentKiller(), // DataSegmentMover
    null, // DataSegmentArchiver
    null, new TestDataSegmentAnnouncer(), EasyMock.createNiceMock(DataSegmentServerAnnouncer.class), handoffNotifierFactory, () -> conglomerate, // queryExecutorService
    DirectQueryProcessingPool.INSTANCE, NoopJoinableFactory.INSTANCE, () -> EasyMock.createMock(MonitorScheduler.class), new SegmentCacheManagerFactory(testUtils.getTestObjectMapper()), testUtils.getTestObjectMapper(), testUtils.getTestIndexIO(), MapCache.create(1024), new CacheConfig(), new CachePopulatorStats(), testUtils.getTestIndexMergerV9(), EasyMock.createNiceMock(DruidNodeAnnouncer.class), EasyMock.createNiceMock(DruidNode.class), new LookupNodeService("tier"), new DataNodeService("tier", 1000, ServerType.INDEXER_EXECUTOR, 0), new SingleFileTaskReportFileWriter(reportsFile), null, AuthTestUtils.TEST_AUTHORIZER_MAPPER, new NoopChatHandlerProvider(), testUtils.getRowIngestionMetersFactory(), new TestAppenderatorsManager(), new NoopIndexingServiceClient(), null, null, null);
}

Example 2 with SegmentHandoffNotifier

use of org.apache.druid.segment.handoff.SegmentHandoffNotifier in project druid by druid-io.

the class IndexTaskTest method testWaitForSegmentAvailabilityMultipleSegmentsTimeout.

@Test
public void testWaitForSegmentAvailabilityMultipleSegmentsTimeout() throws IOException {
    final File tmpDir = temporaryFolder.newFolder();
    TaskToolbox mockToolbox = EasyMock.createMock(TaskToolbox.class);
    SegmentHandoffNotifierFactory mockFactory = EasyMock.createMock(SegmentHandoffNotifierFactory.class);
    SegmentHandoffNotifier mockNotifier = EasyMock.createMock(SegmentHandoffNotifier.class);
    DataSegment mockDataSegment1 = EasyMock.createMock(DataSegment.class);
    DataSegment mockDataSegment2 = EasyMock.createMock(DataSegment.class);
    List<DataSegment> segmentsToWaitFor = new ArrayList<>();
    segmentsToWaitFor.add(mockDataSegment1);
    segmentsToWaitFor.add(mockDataSegment2);
    IndexTask indexTask = new IndexTask(null, null, createDefaultIngestionSpec(jsonMapper, tmpDir, new UniformGranularitySpec(Granularities.HOUR, Granularities.MINUTE, null), null, createTuningConfigWithMaxRowsPerSegment(2, true), false, false), null);
    EasyMock.expect(mockDataSegment1.getInterval()).andReturn(Intervals.of("1970-01-01/2100-01-01")).once();
    EasyMock.expect(mockDataSegment1.getVersion()).andReturn("dummyString").once();
    EasyMock.expect(mockDataSegment1.getShardSpec()).andReturn(EasyMock.createMock(ShardSpec.class)).once();
    EasyMock.expect(mockDataSegment2.getInterval()).andReturn(Intervals.of("1970-01-01/2100-01-01")).once();
    EasyMock.expect(mockDataSegment2.getVersion()).andReturn("dummyString").once();
    EasyMock.expect(mockDataSegment2.getShardSpec()).andReturn(EasyMock.createMock(ShardSpec.class)).once();
    EasyMock.expect(mockToolbox.getSegmentHandoffNotifierFactory()).andReturn(mockFactory).once();
    EasyMock.expect(mockToolbox.getEmitter()).andReturn(new NoopServiceEmitter()).anyTimes();
    EasyMock.expect(mockDataSegment1.getDataSource()).andReturn("MockDataSource").once();
    EasyMock.expect(mockFactory.createSegmentHandoffNotifier("MockDataSource")).andReturn(mockNotifier).once();
    mockNotifier.start();
    EasyMock.expectLastCall().once();
    mockNotifier.registerSegmentHandoffCallback(EasyMock.anyObject(), EasyMock.anyObject(), EasyMock.anyObject());
    EasyMock.expectLastCall().andReturn(true).times(2);
    mockNotifier.close();
    EasyMock.expectLastCall().once();
    EasyMock.replay(mockToolbox);
    EasyMock.replay(mockDataSegment1, mockDataSegment2);
    EasyMock.replay(mockFactory, mockNotifier);
    Assert.assertFalse(indexTask.waitForSegmentAvailability(mockToolbox, segmentsToWaitFor, 1000));
    EasyMock.verify(mockToolbox);
    EasyMock.verify(mockDataSegment1, mockDataSegment2);
    EasyMock.verify(mockFactory, mockNotifier);
}

Example 3 with SegmentHandoffNotifier

use of org.apache.druid.segment.handoff.SegmentHandoffNotifier in project druid by druid-io.

the class KinesisIndexTaskTest method makeToolboxFactory.

private void makeToolboxFactory() throws IOException {
    directory = tempFolder.newFolder();
    final TestUtils testUtils = new TestUtils();
    final ObjectMapper objectMapper = testUtils.getTestObjectMapper();
    objectMapper.setInjectableValues(((InjectableValues.Std) objectMapper.getInjectableValues()).addValue(AWSCredentialsConfig.class, new AWSCredentialsConfig()));
    for (Module module : new KinesisIndexingServiceModule().getJacksonModules()) {
        objectMapper.registerModule(module);
    }
    final TaskConfig taskConfig = new TaskConfig(new File(directory, "baseDir").getPath(), new File(directory, "baseTaskDir").getPath(), null, 50000, null, true, null, null, null, false, false, TaskConfig.BATCH_PROCESSING_MODE_DEFAULT.name());
    final TestDerbyConnector derbyConnector = derby.getConnector();
    derbyConnector.createDataSourceTable();
    derbyConnector.createPendingSegmentsTable();
    derbyConnector.createSegmentTable();
    derbyConnector.createRulesTable();
    derbyConnector.createConfigTable();
    derbyConnector.createTaskTables();
    derbyConnector.createAuditTable();
    taskStorage = new MetadataTaskStorage(derbyConnector, new TaskStorageConfig(null), new DerbyMetadataStorageActionHandlerFactory(derbyConnector, derby.metadataTablesConfigSupplier().get(), objectMapper));
    metadataStorageCoordinator = new IndexerSQLMetadataStorageCoordinator(testUtils.getTestObjectMapper(), derby.metadataTablesConfigSupplier().get(), derbyConnector);
    taskLockbox = new TaskLockbox(taskStorage, metadataStorageCoordinator);
    final TaskActionToolbox taskActionToolbox = new TaskActionToolbox(taskLockbox, taskStorage, metadataStorageCoordinator, emitter, new SupervisorManager(null) {

        @Override
        public boolean checkPointDataSourceMetadata(String supervisorId, int taskGroupId, @Nullable DataSourceMetadata checkpointMetadata) {
            LOG.info("Adding checkpoint hash to the set");
            checkpointRequestsHash.add(Objects.hash(supervisorId, taskGroupId, checkpointMetadata));
            return true;
        }
    });
    final TaskActionClientFactory taskActionClientFactory = new LocalTaskActionClientFactory(taskStorage, taskActionToolbox, new TaskAuditLogConfig(false));
    final SegmentHandoffNotifierFactory handoffNotifierFactory = dataSource -> new SegmentHandoffNotifier() {

        @Override
        public boolean registerSegmentHandoffCallback(SegmentDescriptor descriptor, Executor exec, Runnable handOffRunnable) {
            if (doHandoff) {
                // Simulate immediate handoff
                exec.execute(handOffRunnable);
            }
            return true;
        }

        @Override
        public void start() {
        // Noop
        }

        @Override
        public void close() {
        // Noop
        }
    };
    final LocalDataSegmentPusherConfig dataSegmentPusherConfig = new LocalDataSegmentPusherConfig();
    dataSegmentPusherConfig.storageDirectory = getSegmentDirectory();
    final DataSegmentPusher dataSegmentPusher = new LocalDataSegmentPusher(dataSegmentPusherConfig);
    toolboxFactory = new TaskToolboxFactory(taskConfig, // taskExecutorNode
    null, taskActionClientFactory, emitter, dataSegmentPusher, new TestDataSegmentKiller(), // DataSegmentMover
    null, // DataSegmentArchiver
    null, new TestDataSegmentAnnouncer(), EasyMock.createNiceMock(DataSegmentServerAnnouncer.class), handoffNotifierFactory, this::makeTimeseriesOnlyConglomerate, DirectQueryProcessingPool.INSTANCE, NoopJoinableFactory.INSTANCE, () -> EasyMock.createMock(MonitorScheduler.class), new SegmentCacheManagerFactory(testUtils.getTestObjectMapper()), testUtils.getTestObjectMapper(), testUtils.getTestIndexIO(), MapCache.create(1024), new CacheConfig(), new CachePopulatorStats(), testUtils.getTestIndexMergerV9(), EasyMock.createNiceMock(DruidNodeAnnouncer.class), EasyMock.createNiceMock(DruidNode.class), new LookupNodeService("tier"), new DataNodeService("tier", 1, ServerType.INDEXER_EXECUTOR, 0), new SingleFileTaskReportFileWriter(reportsFile), null, AuthTestUtils.TEST_AUTHORIZER_MAPPER, new NoopChatHandlerProvider(), testUtils.getRowIngestionMetersFactory(), new TestAppenderatorsManager(), new NoopIndexingServiceClient(), null, null, null);
}

Example 4 with SegmentHandoffNotifier

use of org.apache.druid.segment.handoff.SegmentHandoffNotifier in project druid by druid-io.

the class RealtimeIndexTaskTest method makeToolbox.

private TaskToolbox makeToolbox(final Task task, final TaskStorage taskStorage, final IndexerMetadataStorageCoordinator mdc, final File directory) {
    final TaskConfig taskConfig = new TaskConfig(directory.getPath(), null, null, 50000, null, true, null, null, null, false, false, TaskConfig.BATCH_PROCESSING_MODE_DEFAULT.name());
    final TaskLockbox taskLockbox = new TaskLockbox(taskStorage, mdc);
    try {
        taskStorage.insert(task, TaskStatus.running(task.getId()));
    } catch (EntryExistsException e) {
    // suppress
    }
    taskLockbox.syncFromStorage();
    final TaskActionToolbox taskActionToolbox = new TaskActionToolbox(taskLockbox, taskStorage, mdc, EMITTER, EasyMock.createMock(SupervisorManager.class));
    final TaskActionClientFactory taskActionClientFactory = new LocalTaskActionClientFactory(taskStorage, taskActionToolbox, new TaskAuditLogConfig(false));
    final QueryRunnerFactoryConglomerate conglomerate = new DefaultQueryRunnerFactoryConglomerate(ImmutableMap.of(TimeseriesQuery.class, new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(), new TimeseriesQueryEngine(), new QueryWatcher() {

        @Override
        public void registerQueryFuture(Query query, ListenableFuture future) {
        // do nothing
        }
    })));
    handOffCallbacks = new ConcurrentHashMap<>();
    final SegmentHandoffNotifierFactory handoffNotifierFactory = new SegmentHandoffNotifierFactory() {

        @Override
        public SegmentHandoffNotifier createSegmentHandoffNotifier(String dataSource) {
            return new SegmentHandoffNotifier() {

                @Override
                public boolean registerSegmentHandoffCallback(SegmentDescriptor descriptor, Executor exec, Runnable handOffRunnable) {
                    handOffCallbacks.put(descriptor, new Pair<>(exec, handOffRunnable));
                    return true;
                }

                @Override
                public void start() {
                // Noop
                }

                @Override
                public void close() {
                // Noop
                }
            };
        }
    };
    final TestUtils testUtils = new TestUtils();
    final TaskToolboxFactory toolboxFactory = new TaskToolboxFactory(taskConfig, // taskExecutorNode
    null, taskActionClientFactory, EMITTER, new TestDataSegmentPusher(), new TestDataSegmentKiller(), // DataSegmentMover
    null, // DataSegmentArchiver
    null, new TestDataSegmentAnnouncer(), EasyMock.createNiceMock(DataSegmentServerAnnouncer.class), handoffNotifierFactory, () -> conglomerate, DirectQueryProcessingPool.INSTANCE, NoopJoinableFactory.INSTANCE, () -> EasyMock.createMock(MonitorScheduler.class), new SegmentCacheManagerFactory(testUtils.getTestObjectMapper()), testUtils.getTestObjectMapper(), testUtils.getTestIndexIO(), MapCache.create(1024), new CacheConfig(), new CachePopulatorStats(), testUtils.getTestIndexMergerV9(), EasyMock.createNiceMock(DruidNodeAnnouncer.class), EasyMock.createNiceMock(DruidNode.class), new LookupNodeService("tier"), new DataNodeService("tier", 1000, ServerType.INDEXER_EXECUTOR, 0), new NoopTestTaskReportFileWriter(), null, AuthTestUtils.TEST_AUTHORIZER_MAPPER, new NoopChatHandlerProvider(), testUtils.getRowIngestionMetersFactory(), new TestAppenderatorsManager(), new NoopIndexingServiceClient(), null, null, null);
    return toolboxFactory.build(task);
}

Example 5 with SegmentHandoffNotifier

use of org.apache.druid.segment.handoff.SegmentHandoffNotifier in project druid by druid-io.

the class AbstractBatchIndexTask method waitForSegmentAvailability.

/**
 * Wait for segments to become available on the cluster. If waitTimeout is reached, giveup on waiting. This is a
 * QoS method that can be used to make Batch Ingest tasks wait to finish until their ingested data is available on
 * the cluster. Doing so gives an end user assurance that a Successful task status means their data is available
 * for querying.
 *
 * @param toolbox {@link TaskToolbox} object with for assisting with task work.
 * @param segmentsToWaitFor {@link List} of segments to wait for availability.
 * @param waitTimeout Millis to wait before giving up
 * @return True if all segments became available, otherwise False.
 */
protected boolean waitForSegmentAvailability(TaskToolbox toolbox, List<DataSegment> segmentsToWaitFor, long waitTimeout) {
    if (segmentsToWaitFor.isEmpty()) {
        log.info("Asked to wait for segments to be available, but I wasn't provided with any segments.");
        return true;
    } else if (waitTimeout < 0) {
        log.warn("Asked to wait for availability for < 0 seconds?! Requested waitTimeout: [%s]", waitTimeout);
        return false;
    }
    log.info("Waiting for [%d] segments to be loaded by the cluster...", segmentsToWaitFor.size());
    final long start = System.nanoTime();
    try (SegmentHandoffNotifier notifier = toolbox.getSegmentHandoffNotifierFactory().createSegmentHandoffNotifier(segmentsToWaitFor.get(0).getDataSource())) {
        ExecutorService exec = Execs.directExecutor();
        CountDownLatch doneSignal = new CountDownLatch(segmentsToWaitFor.size());
        notifier.start();
        for (DataSegment s : segmentsToWaitFor) {
            notifier.registerSegmentHandoffCallback(new SegmentDescriptor(s.getInterval(), s.getVersion(), s.getShardSpec().getPartitionNum()), exec, () -> {
                log.debug("Confirmed availability for [%s]. Removing from list of segments to wait for", s.getId());
                doneSignal.countDown();
            });
        }
        segmentAvailabilityConfirmationCompleted = doneSignal.await(waitTimeout, TimeUnit.MILLISECONDS);
        return segmentAvailabilityConfirmationCompleted;
    } catch (InterruptedException e) {
        log.warn("Interrupted while waiting for segment availablity; Unable to confirm availability!");
        Thread.currentThread().interrupt();
        return false;
    } finally {
        segmentAvailabilityWaitTimeMs = TimeUnit.NANOSECONDS.toMillis(System.nanoTime() - start);
        toolbox.getEmitter().emit(new ServiceMetricEvent.Builder().setDimension("dataSource", getDataSource()).setDimension("taskType", getType()).setDimension("taskId", getId()).setDimension("segmentAvailabilityConfirmed", segmentAvailabilityConfirmationCompleted).build("task/segmentAvailability/wait/time", segmentAvailabilityWaitTimeMs));
    }
}