Search in sources :

Example 11 with DataSegmentPusher

use of org.apache.druid.segment.loading.DataSegmentPusher in project hive by apache.

the class DruidStorageHandler method loadAndCommitDruidSegments.

/**
 * Creates metadata moves then commit the Segment's metadata to Druid metadata store in one TxN.
 *
 * @param table Hive table
 * @param overwrite true if it is an insert overwrite table.
 */
private List<DataSegment> loadAndCommitDruidSegments(Table table, boolean overwrite, List<DataSegment> segmentsToLoad) throws IOException, CallbackFailedException {
    final String dataSourceName = table.getParameters().get(Constants.DRUID_DATA_SOURCE);
    final String segmentDirectory = table.getParameters().get(DruidConstants.DRUID_SEGMENT_DIRECTORY) != null ? table.getParameters().get(DruidConstants.DRUID_SEGMENT_DIRECTORY) : HiveConf.getVar(getConf(), HiveConf.ConfVars.DRUID_SEGMENT_DIRECTORY);
    final HdfsDataSegmentPusherConfig hdfsSegmentPusherConfig = new HdfsDataSegmentPusherConfig();
    List<DataSegment> publishedDataSegmentList;
    LOG.info(String.format("Moving [%s] Druid segments from staging directory [%s] to Deep storage [%s]", segmentsToLoad.size(), getStagingWorkingDir().toString(), segmentDirectory));
    hdfsSegmentPusherConfig.setStorageDirectory(segmentDirectory);
    DataSegmentPusher dataSegmentPusher = new HdfsDataSegmentPusher(hdfsSegmentPusherConfig, getConf(), JSON_MAPPER);
    publishedDataSegmentList = DruidStorageHandlerUtils.publishSegmentsAndCommit(getConnector(), getDruidMetadataStorageTablesConfig(), dataSourceName, segmentsToLoad, overwrite, getConf(), dataSegmentPusher);
    return publishedDataSegmentList;
}
Also used : DataSegmentPusher(org.apache.druid.segment.loading.DataSegmentPusher) HdfsDataSegmentPusher(org.apache.druid.storage.hdfs.HdfsDataSegmentPusher) HdfsDataSegmentPusherConfig(org.apache.druid.storage.hdfs.HdfsDataSegmentPusherConfig) DataSegment(org.apache.druid.timeline.DataSegment) HdfsDataSegmentPusher(org.apache.druid.storage.hdfs.HdfsDataSegmentPusher)

Example 12 with DataSegmentPusher

use of org.apache.druid.segment.loading.DataSegmentPusher in project druid by druid-io.

the class PartialSegmentMergeTask method mergeAndPushSegments.

private Set<DataSegment> mergeAndPushSegments(TaskToolbox toolbox, DataSchema dataSchema, ParallelIndexTuningConfig tuningConfig, File persistDir, Map<Interval, String> intervalToVersion, Map<Interval, Int2ObjectMap<List<File>>> intervalToUnzippedFiles) throws Exception {
    final DataSegmentPusher segmentPusher = toolbox.getSegmentPusher();
    final Set<DataSegment> pushedSegments = new HashSet<>();
    for (Entry<Interval, Int2ObjectMap<List<File>>> entryPerInterval : intervalToUnzippedFiles.entrySet()) {
        final Interval interval = entryPerInterval.getKey();
        for (Int2ObjectMap.Entry<List<File>> entryPerBucketId : entryPerInterval.getValue().int2ObjectEntrySet()) {
            final int bucketId = entryPerBucketId.getIntKey();
            final List<File> segmentFilesToMerge = entryPerBucketId.getValue();
            final Pair<File, List<String>> mergedFileAndDimensionNames = mergeSegmentsInSamePartition(dataSchema, tuningConfig, toolbox.getIndexIO(), toolbox.getIndexMergerV9(), segmentFilesToMerge, tuningConfig.getMaxNumSegmentsToMerge(), persistDir, 0);
            final List<String> metricNames = Arrays.stream(dataSchema.getAggregators()).map(AggregatorFactory::getName).collect(Collectors.toList());
            // Retry pushing segments because uploading to deep storage might fail especially for cloud storage types
            final DataSegment segment = RetryUtils.retry(() -> segmentPusher.push(mergedFileAndDimensionNames.lhs, new DataSegment(getDataSource(), interval, Preconditions.checkNotNull(ParallelIndexSupervisorTask.findVersion(intervalToVersion, interval), "version for interval[%s]", interval), // will be filled in the segmentPusher
            null, mergedFileAndDimensionNames.rhs, metricNames, createShardSpec(toolbox, interval, bucketId), // will be filled in the segmentPusher
            null, // will be filled in the segmentPusher
            0), false), exception -> !(exception instanceof NullPointerException) && exception instanceof Exception, 5);
            pushedSegments.add(segment);
        }
    }
    return pushedSegments;
}
Also used : DataSegmentPusher(org.apache.druid.segment.loading.DataSegmentPusher) Int2ObjectMap(it.unimi.dsi.fastutil.ints.Int2ObjectMap) DataSegment(org.apache.druid.timeline.DataSegment) IOException(java.io.IOException) ArrayList(java.util.ArrayList) List(java.util.List) File(java.io.File) HashSet(java.util.HashSet) Interval(org.joda.time.Interval)

Example 13 with DataSegmentPusher

use of org.apache.druid.segment.loading.DataSegmentPusher in project druid by druid-io.

the class KafkaIndexTaskTest method makeToolboxFactory.

private void makeToolboxFactory() throws IOException {
    directory = tempFolder.newFolder();
    final TestUtils testUtils = new TestUtils();
    rowIngestionMetersFactory = testUtils.getRowIngestionMetersFactory();
    final ObjectMapper objectMapper = testUtils.getTestObjectMapper();
    for (Module module : new KafkaIndexTaskModule().getJacksonModules()) {
        objectMapper.registerModule(module);
    }
    objectMapper.registerModule(TEST_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 previousDataSourceMetadata) {
            log.info("Adding checkpoint hash to the set");
            checkpointRequestsHash.add(Objects.hash(supervisorId, taskGroupId, previousDataSourceMetadata));
            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::makeTimeseriesAndScanConglomerate, 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);
}
Also used : JsonProperty(com.fasterxml.jackson.annotation.JsonProperty) SegmentCacheManagerFactory(org.apache.druid.indexing.common.SegmentCacheManagerFactory) DirectQueryProcessingPool(org.apache.druid.query.DirectQueryProcessingPool) Arrays(java.util.Arrays) LookupNodeService(org.apache.druid.discovery.LookupNodeService) TestDataSegmentAnnouncer(org.apache.druid.indexing.test.TestDataSegmentAnnouncer) DataSourceMetadata(org.apache.druid.indexing.overlord.DataSourceMetadata) Map(java.util.Map) NamedType(com.fasterxml.jackson.databind.jsontype.NamedType) ScanQueryQueryToolChest(org.apache.druid.query.scan.ScanQueryQueryToolChest) ExpressionTransform(org.apache.druid.segment.transform.ExpressionTransform) AppenderatorsManager(org.apache.druid.segment.realtime.appenderator.AppenderatorsManager) NoopJoinableFactory(org.apache.druid.segment.join.NoopJoinableFactory) NoopIndexingServiceClient(org.apache.druid.client.indexing.NoopIndexingServiceClient) AfterClass(org.junit.AfterClass) Execs(org.apache.druid.java.util.common.concurrent.Execs) InputFormat(org.apache.druid.data.input.InputFormat) IngestionStatsAndErrorsTaskReportData(org.apache.druid.indexing.common.IngestionStatsAndErrorsTaskReportData) CacheConfig(org.apache.druid.client.cache.CacheConfig) TimeseriesQuery(org.apache.druid.query.timeseries.TimeseriesQuery) Set(java.util.Set) StringDimensionSchema(org.apache.druid.data.input.impl.StringDimensionSchema) StandardCharsets(java.nio.charset.StandardCharsets) Executors(java.util.concurrent.Executors) InputRow(org.apache.druid.data.input.InputRow) TaskState(org.apache.druid.indexer.TaskState) Stream(java.util.stream.Stream) TestDerbyConnector(org.apache.druid.metadata.TestDerbyConnector) TaskActionClientFactory(org.apache.druid.indexing.common.actions.TaskActionClientFactory) RowIngestionMetersFactory(org.apache.druid.segment.incremental.RowIngestionMetersFactory) TestingCluster(org.apache.curator.test.TestingCluster) TestBroker(org.apache.druid.indexing.kafka.test.TestBroker) TransformSpec(org.apache.druid.segment.transform.TransformSpec) DataSegmentPusher(org.apache.druid.segment.loading.DataSegmentPusher) Iterables(com.google.common.collect.Iterables) DoubleSumAggregatorFactory(org.apache.druid.query.aggregation.DoubleSumAggregatorFactory) SeekableStreamIndexTaskTestBase(org.apache.druid.indexing.seekablestream.SeekableStreamIndexTaskTestBase) DruidNodeAnnouncer(org.apache.druid.discovery.DruidNodeAnnouncer) RunWith(org.junit.runner.RunWith) TaskAuditLogConfig(org.apache.druid.indexing.common.actions.TaskAuditLogConfig) InputRowListPlusRawValues(org.apache.druid.data.input.InputRowListPlusRawValues) InputRowSchema(org.apache.druid.data.input.InputRowSchema) TaskStatus(org.apache.druid.indexer.TaskStatus) ScanQuery(org.apache.druid.query.scan.ScanQuery) KafkaSupervisorIOConfig(org.apache.druid.indexing.kafka.supervisor.KafkaSupervisorIOConfig) LinkedHashMap(java.util.LinkedHashMap) LocalDataSegmentPusherConfig(org.apache.druid.segment.loading.LocalDataSegmentPusherConfig) SupervisorManager(org.apache.druid.indexing.overlord.supervisor.SupervisorManager) AuthTestUtils(org.apache.druid.server.security.AuthTestUtils) CachePopulatorStats(org.apache.druid.client.cache.CachePopulatorStats) Nullable(javax.annotation.Nullable) Before(org.junit.Before) SeekableStreamEndSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers) TaskToolboxFactory(org.apache.druid.indexing.common.TaskToolboxFactory) Executor(java.util.concurrent.Executor) DataSegmentServerAnnouncer(org.apache.druid.server.coordination.DataSegmentServerAnnouncer) QueryRunnerFactoryConglomerate(org.apache.druid.query.QueryRunnerFactoryConglomerate) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) Test(org.junit.Test) IOException(java.io.IOException) EasyMock(org.easymock.EasyMock) File(java.io.File) ExecutionException(java.util.concurrent.ExecutionException) Futures(com.google.common.util.concurrent.Futures) KafkaRecordEntity(org.apache.druid.data.input.kafka.KafkaRecordEntity) TreeMap(java.util.TreeMap) DefaultQueryRunnerFactoryConglomerate(org.apache.druid.query.DefaultQueryRunnerFactoryConglomerate) DruidNode(org.apache.druid.server.DruidNode) QueryRunnerFactory(org.apache.druid.query.QueryRunnerFactory) DefaultGenericQueryMetricsFactory(org.apache.druid.query.DefaultGenericQueryMetricsFactory) Assert(org.junit.Assert) DataSchema(org.apache.druid.segment.indexing.DataSchema) Module(com.fasterxml.jackson.databind.Module) QueryPlus(org.apache.druid.query.QueryPlus) TaskConfig(org.apache.druid.indexing.common.config.TaskConfig) LongDimensionSchema(org.apache.druid.data.input.impl.LongDimensionSchema) LocalTaskActionClientFactory(org.apache.druid.indexing.common.actions.LocalTaskActionClientFactory) TimeoutException(java.util.concurrent.TimeoutException) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) SeekableStreamSupervisor(org.apache.druid.indexing.seekablestream.supervisor.SeekableStreamSupervisor) SimpleModule(com.fasterxml.jackson.databind.module.SimpleModule) Druids(org.apache.druid.query.Druids) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) Task(org.apache.druid.indexing.common.task.Task) After(org.junit.After) ServerType(org.apache.druid.server.coordination.ServerType) TypeReference(com.fasterxml.jackson.core.type.TypeReference) CloseableIterator(org.apache.druid.java.util.common.parsers.CloseableIterator) NoopChatHandlerProvider(org.apache.druid.segment.realtime.firehose.NoopChatHandlerProvider) DerbyMetadataStorageActionHandlerFactory(org.apache.druid.metadata.DerbyMetadataStorageActionHandlerFactory) Parameterized(org.junit.runners.Parameterized) SeekableStreamStartSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers) DateTimes(org.apache.druid.java.util.common.DateTimes) ImmutableSet(com.google.common.collect.ImmutableSet) ImmutableMap(com.google.common.collect.ImmutableMap) ScanResultValue(org.apache.druid.query.scan.ScanResultValue) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) Status(org.apache.druid.indexing.seekablestream.SeekableStreamIndexTaskRunner.Status) StringUtils(org.apache.druid.java.util.common.StringUtils) ScanQueryEngine(org.apache.druid.query.scan.ScanQueryEngine) Collectors(java.util.stream.Collectors) LockGranularity(org.apache.druid.indexing.common.LockGranularity) QuerySegmentSpec(org.apache.druid.query.spec.QuerySegmentSpec) TestUtils(org.apache.druid.indexing.common.TestUtils) ExprMacroTable(org.apache.druid.math.expr.ExprMacroTable) IndexerSQLMetadataStorageCoordinator(org.apache.druid.metadata.IndexerSQLMetadataStorageCoordinator) Objects(java.util.Objects) DataNodeService(org.apache.druid.discovery.DataNodeService) List(java.util.List) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) Header(org.apache.kafka.common.header.Header) InputEntityReader(org.apache.druid.data.input.InputEntityReader) ServiceEmitter(org.apache.druid.java.util.emitter.service.ServiceEmitter) SegmentHandoffNotifierFactory(org.apache.druid.segment.handoff.SegmentHandoffNotifierFactory) MetadataTaskStorage(org.apache.druid.indexing.overlord.MetadataTaskStorage) MapCache(org.apache.druid.client.cache.MapCache) Logger(org.apache.druid.java.util.common.logger.Logger) MoreExecutors(com.google.common.util.concurrent.MoreExecutors) TimeseriesQueryEngine(org.apache.druid.query.timeseries.TimeseriesQueryEngine) ProducerRecord(org.apache.kafka.clients.producer.ProducerRecord) ListenableFuture(com.google.common.util.concurrent.ListenableFuture) BeforeClass(org.junit.BeforeClass) SingleFileTaskReportFileWriter(org.apache.druid.indexing.common.SingleFileTaskReportFileWriter) TaskStorageConfig(org.apache.druid.indexing.common.config.TaskStorageConfig) MapBasedInputRow(org.apache.druid.data.input.MapBasedInputRow) HashMap(java.util.HashMap) RowIngestionMeters(org.apache.druid.segment.incremental.RowIngestionMeters) TaskActionToolbox(org.apache.druid.indexing.common.actions.TaskActionToolbox) HashSet(java.util.HashSet) ScanQueryConfig(org.apache.druid.query.scan.ScanQueryConfig) KafkaProducer(org.apache.kafka.clients.producer.KafkaProducer) ImmutableList(com.google.common.collect.ImmutableList) FloatDimensionSchema(org.apache.druid.data.input.impl.FloatDimensionSchema) Query(org.apache.druid.query.Query) NoopEmitter(org.apache.druid.java.util.emitter.core.NoopEmitter) ScanQueryRunnerFactory(org.apache.druid.query.scan.ScanQueryRunnerFactory) KafkaSupervisor(org.apache.druid.indexing.kafka.supervisor.KafkaSupervisor) RowIngestionMetersTotals(org.apache.druid.segment.incremental.RowIngestionMetersTotals) KafkaStringHeaderFormat(org.apache.druid.data.input.kafkainput.KafkaStringHeaderFormat) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) SegmentHandoffNotifier(org.apache.druid.segment.handoff.SegmentHandoffNotifier) Period(org.joda.time.Period) TestAppenderatorsManager(org.apache.druid.indexing.common.task.TestAppenderatorsManager) TaskLockbox(org.apache.druid.indexing.overlord.TaskLockbox) EmittingLogger(org.apache.druid.java.util.emitter.EmittingLogger) IndexTaskTest(org.apache.druid.indexing.common.task.IndexTaskTest) TimeseriesQueryQueryToolChest(org.apache.druid.query.timeseries.TimeseriesQueryQueryToolChest) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) JsonProcessingException(com.fasterxml.jackson.core.JsonProcessingException) TestDataSegmentKiller(org.apache.druid.indexing.test.TestDataSegmentKiller) Granularities(org.apache.druid.java.util.common.granularity.Granularities) TimeUnit(java.util.concurrent.TimeUnit) Rule(org.junit.Rule) KafkaInputFormat(org.apache.druid.data.input.kafkainput.KafkaInputFormat) MonitorScheduler(org.apache.druid.java.util.metrics.MonitorScheduler) JsonCreator(com.fasterxml.jackson.annotation.JsonCreator) LocalDataSegmentPusher(org.apache.druid.segment.loading.LocalDataSegmentPusher) AsyncFunction(com.google.common.util.concurrent.AsyncFunction) SegmentDescriptor(org.apache.druid.query.SegmentDescriptor) TimeseriesQueryRunnerFactory(org.apache.druid.query.timeseries.TimeseriesQueryRunnerFactory) InputEntity(org.apache.druid.data.input.InputEntity) Collections(java.util.Collections) SeekableStreamIndexTaskRunner(org.apache.druid.indexing.seekablestream.SeekableStreamIndexTaskRunner) TemporaryFolder(org.junit.rules.TemporaryFolder) DerbyMetadataStorageActionHandlerFactory(org.apache.druid.metadata.DerbyMetadataStorageActionHandlerFactory) SingleFileTaskReportFileWriter(org.apache.druid.indexing.common.SingleFileTaskReportFileWriter) DataSegmentPusher(org.apache.druid.segment.loading.DataSegmentPusher) LocalDataSegmentPusher(org.apache.druid.segment.loading.LocalDataSegmentPusher) TaskActionClientFactory(org.apache.druid.indexing.common.actions.TaskActionClientFactory) LocalTaskActionClientFactory(org.apache.druid.indexing.common.actions.LocalTaskActionClientFactory) TestDataSegmentAnnouncer(org.apache.druid.indexing.test.TestDataSegmentAnnouncer) TaskConfig(org.apache.druid.indexing.common.config.TaskConfig) TaskAuditLogConfig(org.apache.druid.indexing.common.actions.TaskAuditLogConfig) AuthTestUtils(org.apache.druid.server.security.AuthTestUtils) TestUtils(org.apache.druid.indexing.common.TestUtils) DataSourceMetadata(org.apache.druid.indexing.overlord.DataSourceMetadata) Executor(java.util.concurrent.Executor) NoopIndexingServiceClient(org.apache.druid.client.indexing.NoopIndexingServiceClient) TaskToolboxFactory(org.apache.druid.indexing.common.TaskToolboxFactory) SegmentDescriptor(org.apache.druid.query.SegmentDescriptor) CachePopulatorStats(org.apache.druid.client.cache.CachePopulatorStats) TaskActionToolbox(org.apache.druid.indexing.common.actions.TaskActionToolbox) LocalTaskActionClientFactory(org.apache.druid.indexing.common.actions.LocalTaskActionClientFactory) CacheConfig(org.apache.druid.client.cache.CacheConfig) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) IndexerSQLMetadataStorageCoordinator(org.apache.druid.metadata.IndexerSQLMetadataStorageCoordinator) TaskStorageConfig(org.apache.druid.indexing.common.config.TaskStorageConfig) NoopChatHandlerProvider(org.apache.druid.segment.realtime.firehose.NoopChatHandlerProvider) LocalDataSegmentPusherConfig(org.apache.druid.segment.loading.LocalDataSegmentPusherConfig) SegmentHandoffNotifier(org.apache.druid.segment.handoff.SegmentHandoffNotifier) SegmentCacheManagerFactory(org.apache.druid.indexing.common.SegmentCacheManagerFactory) LookupNodeService(org.apache.druid.discovery.LookupNodeService) TestDerbyConnector(org.apache.druid.metadata.TestDerbyConnector) LocalDataSegmentPusher(org.apache.druid.segment.loading.LocalDataSegmentPusher) TestDataSegmentKiller(org.apache.druid.indexing.test.TestDataSegmentKiller) SegmentHandoffNotifierFactory(org.apache.druid.segment.handoff.SegmentHandoffNotifierFactory) SupervisorManager(org.apache.druid.indexing.overlord.supervisor.SupervisorManager) TaskLockbox(org.apache.druid.indexing.overlord.TaskLockbox) Module(com.fasterxml.jackson.databind.Module) SimpleModule(com.fasterxml.jackson.databind.module.SimpleModule) MetadataTaskStorage(org.apache.druid.indexing.overlord.MetadataTaskStorage) DataNodeService(org.apache.druid.discovery.DataNodeService) File(java.io.File) TestAppenderatorsManager(org.apache.druid.indexing.common.task.TestAppenderatorsManager)

Example 14 with DataSegmentPusher

use of org.apache.druid.segment.loading.DataSegmentPusher in project druid by druid-io.

the class RealtimePlumberSchoolTest method setUp.

@Before
public void setUp() throws Exception {
    tmpDir = FileUtils.createTempDir();
    ObjectMapper jsonMapper = new DefaultObjectMapper();
    schema = new DataSchema("test", jsonMapper.convertValue(new StringInputRowParser(new JSONParseSpec(new TimestampSpec("timestamp", "auto", null), DimensionsSpec.EMPTY, null, null, null), null), Map.class), new AggregatorFactory[] { new CountAggregatorFactory("rows") }, new UniformGranularitySpec(Granularities.HOUR, Granularities.NONE, null), null, jsonMapper);
    schema2 = new DataSchema("test", jsonMapper.convertValue(new StringInputRowParser(new JSONParseSpec(new TimestampSpec("timestamp", "auto", null), DimensionsSpec.EMPTY, null, null, null), null), Map.class), new AggregatorFactory[] { new CountAggregatorFactory("rows") }, new UniformGranularitySpec(Granularities.YEAR, Granularities.NONE, null), null, jsonMapper);
    announcer = EasyMock.createMock(DataSegmentAnnouncer.class);
    announcer.announceSegment(EasyMock.anyObject());
    EasyMock.expectLastCall().anyTimes();
    segmentPublisher = EasyMock.createNiceMock(SegmentPublisher.class);
    dataSegmentPusher = EasyMock.createNiceMock(DataSegmentPusher.class);
    handoffNotifierFactory = EasyMock.createNiceMock(SegmentHandoffNotifierFactory.class);
    handoffNotifier = EasyMock.createNiceMock(SegmentHandoffNotifier.class);
    EasyMock.expect(handoffNotifierFactory.createSegmentHandoffNotifier(EasyMock.anyString())).andReturn(handoffNotifier).anyTimes();
    EasyMock.expect(handoffNotifier.registerSegmentHandoffCallback(EasyMock.anyObject(), EasyMock.anyObject(), EasyMock.anyObject())).andReturn(true).anyTimes();
    emitter = EasyMock.createMock(ServiceEmitter.class);
    EasyMock.replay(announcer, segmentPublisher, dataSegmentPusher, handoffNotifierFactory, handoffNotifier, emitter);
    tuningConfig = new RealtimeTuningConfig(null, 1, null, null, null, null, null, new IntervalStartVersioningPolicy(), rejectionPolicy, null, null, null, null, 0, 0, false, null, null, null, null);
    realtimePlumberSchool = new RealtimePlumberSchool(emitter, new DefaultQueryRunnerFactoryConglomerate(new HashMap<>()), dataSegmentPusher, announcer, segmentPublisher, handoffNotifierFactory, DirectQueryProcessingPool.INSTANCE, NoopJoinableFactory.INSTANCE, TestHelper.getTestIndexMergerV9(segmentWriteOutMediumFactory), TestHelper.getTestIndexIO(), MapCache.create(0), FireDepartmentTest.NO_CACHE_CONFIG, new CachePopulatorStats(), TestHelper.makeJsonMapper());
    metrics = new FireDepartmentMetrics();
    plumber = (RealtimePlumber) realtimePlumberSchool.findPlumber(schema, tuningConfig, metrics);
}
Also used : ServiceEmitter(org.apache.druid.java.util.emitter.service.ServiceEmitter) DataSegmentPusher(org.apache.druid.segment.loading.DataSegmentPusher) DataSegmentAnnouncer(org.apache.druid.server.coordination.DataSegmentAnnouncer) SegmentHandoffNotifier(org.apache.druid.segment.handoff.SegmentHandoffNotifier) DefaultQueryRunnerFactoryConglomerate(org.apache.druid.query.DefaultQueryRunnerFactoryConglomerate) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) RealtimeTuningConfig(org.apache.druid.segment.indexing.RealtimeTuningConfig) SegmentHandoffNotifierFactory(org.apache.druid.segment.handoff.SegmentHandoffNotifierFactory) DataSchema(org.apache.druid.segment.indexing.DataSchema) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) SegmentPublisher(org.apache.druid.segment.realtime.SegmentPublisher) FireDepartmentMetrics(org.apache.druid.segment.realtime.FireDepartmentMetrics) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) CachePopulatorStats(org.apache.druid.client.cache.CachePopulatorStats) StringInputRowParser(org.apache.druid.data.input.impl.StringInputRowParser) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DefaultObjectMapper(org.apache.druid.jackson.DefaultObjectMapper) JSONParseSpec(org.apache.druid.data.input.impl.JSONParseSpec) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) DefaultObjectMapper(org.apache.druid.jackson.DefaultObjectMapper) Before(org.junit.Before)

Aggregations

DataSegmentPusher (org.apache.druid.segment.loading.DataSegmentPusher)14 DataSegment (org.apache.druid.timeline.DataSegment)11 Test (org.junit.Test)11 File (java.io.File)9 Interval (org.joda.time.Interval)9 HdfsDataSegmentPusher (org.apache.druid.storage.hdfs.HdfsDataSegmentPusher)8 HdfsDataSegmentPusherConfig (org.apache.druid.storage.hdfs.HdfsDataSegmentPusherConfig)8 LocalFileSystem (org.apache.hadoop.fs.LocalFileSystem)8 Path (org.apache.hadoop.fs.Path)8 MetadataStorageTablesConfig (org.apache.druid.metadata.MetadataStorageTablesConfig)7 LinearShardSpec (org.apache.druid.timeline.partition.LinearShardSpec)7 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)4 ImmutableMap (com.google.common.collect.ImmutableMap)4 IOException (java.io.IOException)4 List (java.util.List)4 DataSchema (org.apache.druid.segment.indexing.DataSchema)4 ImmutableList (com.google.common.collect.ImmutableList)3 Map (java.util.Map)3 JsonCreator (com.fasterxml.jackson.annotation.JsonCreator)2 JsonProperty (com.fasterxml.jackson.annotation.JsonProperty)2