Search in sources :

Example 1 with TaskPayloadResponse

use of org.apache.druid.client.indexing.TaskPayloadResponse in project druid by druid-io.

the class CompactSegments method run.

@Override
public DruidCoordinatorRuntimeParams run(DruidCoordinatorRuntimeParams params) {
    LOG.info("Compact segments");
    final CoordinatorCompactionConfig dynamicConfig = params.getCoordinatorCompactionConfig();
    final CoordinatorStats stats = new CoordinatorStats();
    List<DataSourceCompactionConfig> compactionConfigList = dynamicConfig.getCompactionConfigs();
    if (dynamicConfig.getMaxCompactionTaskSlots() > 0) {
        Map<String, VersionedIntervalTimeline<String, DataSegment>> dataSources = params.getUsedSegmentsTimelinesPerDataSource();
        if (compactionConfigList != null && !compactionConfigList.isEmpty()) {
            Map<String, DataSourceCompactionConfig> compactionConfigs = compactionConfigList.stream().collect(Collectors.toMap(DataSourceCompactionConfig::getDataSource, Function.identity()));
            final List<TaskStatusPlus> compactionTasks = filterNonCompactionTasks(indexingServiceClient.getActiveTasks());
            // dataSource -> list of intervals for which compaction will be skipped in this run
            final Map<String, List<Interval>> intervalsToSkipCompaction = new HashMap<>();
            int numEstimatedNonCompleteCompactionTasks = 0;
            for (TaskStatusPlus status : compactionTasks) {
                final TaskPayloadResponse response = indexingServiceClient.getTaskPayload(status.getId());
                if (response == null) {
                    throw new ISE("Got a null paylord from overlord for task[%s]", status.getId());
                }
                if (COMPACTION_TASK_TYPE.equals(response.getPayload().getType())) {
                    final ClientCompactionTaskQuery compactionTaskQuery = (ClientCompactionTaskQuery) response.getPayload();
                    DataSourceCompactionConfig dataSourceCompactionConfig = compactionConfigs.get(status.getDataSource());
                    if (dataSourceCompactionConfig != null && dataSourceCompactionConfig.getGranularitySpec() != null) {
                        Granularity configuredSegmentGranularity = dataSourceCompactionConfig.getGranularitySpec().getSegmentGranularity();
                        if (configuredSegmentGranularity != null && compactionTaskQuery.getGranularitySpec() != null && !configuredSegmentGranularity.equals(compactionTaskQuery.getGranularitySpec().getSegmentGranularity())) {
                            // We will cancel active compaction task if segmentGranularity changes and we will need to
                            // re-compact the interval
                            LOG.info("Canceled task[%s] as task segmentGranularity is [%s] but compaction config " + "segmentGranularity is [%s]", status.getId(), compactionTaskQuery.getGranularitySpec().getSegmentGranularity(), configuredSegmentGranularity);
                            indexingServiceClient.cancelTask(status.getId());
                            continue;
                        }
                    }
                    // Skip interval as the current active compaction task is good
                    final Interval interval = compactionTaskQuery.getIoConfig().getInputSpec().getInterval();
                    intervalsToSkipCompaction.computeIfAbsent(status.getDataSource(), k -> new ArrayList<>()).add(interval);
                    // Since we keep the current active compaction task running, we count the active task slots
                    numEstimatedNonCompleteCompactionTasks += findMaxNumTaskSlotsUsedByOneCompactionTask(compactionTaskQuery.getTuningConfig());
                } else {
                    throw new ISE("task[%s] is not a compactionTask", status.getId());
                }
            }
            // Skip all the intervals locked by higher priority tasks for each datasource
            // This must be done after the invalid compaction tasks are cancelled
            // in the loop above so that their intervals are not considered locked
            getLockedIntervalsToSkip(compactionConfigList).forEach((dataSource, intervals) -> intervalsToSkipCompaction.computeIfAbsent(dataSource, ds -> new ArrayList<>()).addAll(intervals));
            final CompactionSegmentIterator iterator = policy.reset(compactionConfigs, dataSources, intervalsToSkipCompaction);
            int totalCapacity;
            if (dynamicConfig.isUseAutoScaleSlots()) {
                try {
                    totalCapacity = indexingServiceClient.getTotalWorkerCapacityWithAutoScale();
                } catch (Exception e) {
                    LOG.warn("Failed to get total worker capacity with auto scale slots. Falling back to current capacity count");
                    totalCapacity = indexingServiceClient.getTotalWorkerCapacity();
                }
            } else {
                totalCapacity = indexingServiceClient.getTotalWorkerCapacity();
            }
            final int compactionTaskCapacity = (int) Math.min(totalCapacity * dynamicConfig.getCompactionTaskSlotRatio(), dynamicConfig.getMaxCompactionTaskSlots());
            final int numAvailableCompactionTaskSlots;
            if (numEstimatedNonCompleteCompactionTasks > 0) {
                numAvailableCompactionTaskSlots = Math.max(0, compactionTaskCapacity - numEstimatedNonCompleteCompactionTasks);
            } else {
                // compactionTaskCapacity might be 0 if totalWorkerCapacity is low.
                // This guarantees that at least one slot is available if
                // compaction is enabled and numEstimatedNonCompleteCompactionTasks is 0.
                numAvailableCompactionTaskSlots = Math.max(1, compactionTaskCapacity);
            }
            LOG.info("Found [%d] available task slots for compaction out of [%d] max compaction task capacity", numAvailableCompactionTaskSlots, compactionTaskCapacity);
            stats.addToGlobalStat(AVAILABLE_COMPACTION_TASK_SLOT, numAvailableCompactionTaskSlots);
            stats.addToGlobalStat(MAX_COMPACTION_TASK_SLOT, compactionTaskCapacity);
            final Map<String, AutoCompactionSnapshot.Builder> currentRunAutoCompactionSnapshotBuilders = new HashMap<>();
            if (numAvailableCompactionTaskSlots > 0) {
                stats.accumulate(doRun(compactionConfigs, currentRunAutoCompactionSnapshotBuilders, numAvailableCompactionTaskSlots, iterator));
            } else {
                stats.accumulate(makeStats(currentRunAutoCompactionSnapshotBuilders, 0, iterator));
            }
        } else {
            LOG.info("compactionConfig is empty. Skip.");
            autoCompactionSnapshotPerDataSource.set(new HashMap<>());
        }
    } else {
        LOG.info("maxCompactionTaskSlots was set to 0. Skip compaction");
        autoCompactionSnapshotPerDataSource.set(new HashMap<>());
    }
    return params.buildFromExisting().withCoordinatorStats(stats).build();
}
Also used : Logger(org.apache.druid.java.util.common.logger.Logger) Granularity(org.apache.druid.java.util.common.granularity.Granularity) Inject(com.google.inject.Inject) ClientCompactionTaskDimensionsSpec(org.apache.druid.client.indexing.ClientCompactionTaskDimensionsSpec) DruidCoordinatorRuntimeParams(org.apache.druid.server.coordinator.DruidCoordinatorRuntimeParams) IndexingServiceClient(org.apache.druid.client.indexing.IndexingServiceClient) HashMap(java.util.HashMap) CoordinatorStats(org.apache.druid.server.coordinator.CoordinatorStats) AtomicReference(java.util.concurrent.atomic.AtomicReference) Function(java.util.function.Function) AutoCompactionSnapshot(org.apache.druid.server.coordinator.AutoCompactionSnapshot) DataSourceCompactionConfig(org.apache.druid.server.coordinator.DataSourceCompactionConfig) ArrayList(java.util.ArrayList) TaskPayloadResponse(org.apache.druid.client.indexing.TaskPayloadResponse) Interval(org.joda.time.Interval) DruidCoordinatorConfig(org.apache.druid.server.coordinator.DruidCoordinatorConfig) Map(java.util.Map) IAE(org.apache.druid.java.util.common.IAE) DimensionRangePartitionsSpec(org.apache.druid.indexer.partitions.DimensionRangePartitionsSpec) Nullable(javax.annotation.Nullable) ClientCompactionTaskTransformSpec(org.apache.druid.client.indexing.ClientCompactionTaskTransformSpec) JacksonInject(com.fasterxml.jackson.annotation.JacksonInject) VersionedIntervalTimeline(org.apache.druid.timeline.VersionedIntervalTimeline) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) ClientCompactionTaskQueryTuningConfig(org.apache.druid.client.indexing.ClientCompactionTaskQueryTuningConfig) CompactionStatistics(org.apache.druid.server.coordinator.CompactionStatistics) CoordinatorCompactionConfig(org.apache.druid.server.coordinator.CoordinatorCompactionConfig) ISE(org.apache.druid.java.util.common.ISE) Collectors(java.util.stream.Collectors) ClientCompactionTaskQuery(org.apache.druid.client.indexing.ClientCompactionTaskQuery) TaskStatusPlus(org.apache.druid.indexer.TaskStatusPlus) List(java.util.List) ClientCompactionTaskGranularitySpec(org.apache.druid.client.indexing.ClientCompactionTaskGranularitySpec) GranularityType(org.apache.druid.java.util.common.granularity.GranularityType) JsonCreator(com.fasterxml.jackson.annotation.JsonCreator) DataSegment(org.apache.druid.timeline.DataSegment) VisibleForTesting(com.google.common.annotations.VisibleForTesting) CoordinatorStats(org.apache.druid.server.coordinator.CoordinatorStats) CoordinatorCompactionConfig(org.apache.druid.server.coordinator.CoordinatorCompactionConfig) HashMap(java.util.HashMap) ArrayList(java.util.ArrayList) Granularity(org.apache.druid.java.util.common.granularity.Granularity) DataSourceCompactionConfig(org.apache.druid.server.coordinator.DataSourceCompactionConfig) ClientCompactionTaskQuery(org.apache.druid.client.indexing.ClientCompactionTaskQuery) TaskStatusPlus(org.apache.druid.indexer.TaskStatusPlus) ArrayList(java.util.ArrayList) List(java.util.List) ISE(org.apache.druid.java.util.common.ISE) TaskPayloadResponse(org.apache.druid.client.indexing.TaskPayloadResponse) VersionedIntervalTimeline(org.apache.druid.timeline.VersionedIntervalTimeline) Interval(org.joda.time.Interval)

Example 2 with TaskPayloadResponse

use of org.apache.druid.client.indexing.TaskPayloadResponse in project druid by druid-io.

the class CompactSegmentsTest method testCompactWithGranularitySpecConflictWithActiveCompactionTask.

@Test
public void testCompactWithGranularitySpecConflictWithActiveCompactionTask() {
    final String dataSource = DATA_SOURCE_PREFIX + 0;
    final String conflictTaskId = "taskIdDummy";
    final HttpIndexingServiceClient mockIndexingServiceClient = Mockito.mock(HttpIndexingServiceClient.class);
    TaskStatusPlus runningConflictCompactionTask = new TaskStatusPlus(conflictTaskId, "groupId", "compact", DateTimes.EPOCH, DateTimes.EPOCH, TaskState.RUNNING, RunnerTaskState.RUNNING, -1L, TaskLocation.unknown(), dataSource, null);
    TaskPayloadResponse runningConflictCompactionTaskPayload = new TaskPayloadResponse(conflictTaskId, new ClientCompactionTaskQuery(conflictTaskId, dataSource, new ClientCompactionIOConfig(new ClientCompactionIntervalSpec(Intervals.of("2000/2099"), "testSha256OfSortedSegmentIds"), null), null, new ClientCompactionTaskGranularitySpec(Granularities.DAY, null, null), null, null, null, null));
    Mockito.when(mockIndexingServiceClient.getActiveTasks()).thenReturn(ImmutableList.of(runningConflictCompactionTask));
    Mockito.when(mockIndexingServiceClient.getTaskPayload(ArgumentMatchers.eq(conflictTaskId))).thenReturn(runningConflictCompactionTaskPayload);
    final CompactSegments compactSegments = new CompactSegments(COORDINATOR_CONFIG, JSON_MAPPER, mockIndexingServiceClient);
    final List<DataSourceCompactionConfig> compactionConfigs = new ArrayList<>();
    compactionConfigs.add(new DataSourceCompactionConfig(dataSource, 0, 500L, null, // smaller than segment interval
    new Period("PT0H"), new UserCompactionTaskQueryTuningConfig(null, null, null, null, partitionsSpec, null, null, null, null, null, 3, null, null, null, null, null, null), new UserCompactionTaskGranularityConfig(Granularities.YEAR, null, null), null, null, null, null, null));
    doCompactSegments(compactSegments, compactionConfigs);
    // Verify that conflict task was canceled
    Mockito.verify(mockIndexingServiceClient).cancelTask(conflictTaskId);
    // The active conflict task has interval of 2000/2099
    // Make sure that we do not skip interval of conflict task.
    // Since we cancel the task and will have to compact those intervals with the new segmentGranulartity
    ArgumentCaptor<List<DataSegment>> segmentsCaptor = ArgumentCaptor.forClass(List.class);
    ArgumentCaptor<ClientCompactionTaskGranularitySpec> granularitySpecArgumentCaptor = ArgumentCaptor.forClass(ClientCompactionTaskGranularitySpec.class);
    Mockito.verify(mockIndexingServiceClient).compactSegments(ArgumentMatchers.anyString(), segmentsCaptor.capture(), ArgumentMatchers.anyInt(), ArgumentMatchers.any(), granularitySpecArgumentCaptor.capture(), ArgumentMatchers.any(), ArgumentMatchers.any(), ArgumentMatchers.any(), ArgumentMatchers.any(), ArgumentMatchers.any());
    // All segments is compact at the same time since we changed the segment granularity to YEAR and all segment
    // are within the same year
    Assert.assertEquals(datasourceToSegments.get(dataSource).size(), segmentsCaptor.getValue().size());
    ClientCompactionTaskGranularitySpec actual = granularitySpecArgumentCaptor.getValue();
    Assert.assertNotNull(actual);
    ClientCompactionTaskGranularitySpec expected = new ClientCompactionTaskGranularitySpec(Granularities.YEAR, null, null);
    Assert.assertEquals(expected, actual);
}
Also used : ClientCompactionIOConfig(org.apache.druid.client.indexing.ClientCompactionIOConfig) ArrayList(java.util.ArrayList) Period(org.joda.time.Period) UserCompactionTaskQueryTuningConfig(org.apache.druid.server.coordinator.UserCompactionTaskQueryTuningConfig) ClientCompactionTaskGranularitySpec(org.apache.druid.client.indexing.ClientCompactionTaskGranularitySpec) HttpIndexingServiceClient(org.apache.druid.client.indexing.HttpIndexingServiceClient) ClientCompactionIntervalSpec(org.apache.druid.client.indexing.ClientCompactionIntervalSpec) TaskPayloadResponse(org.apache.druid.client.indexing.TaskPayloadResponse) DataSourceCompactionConfig(org.apache.druid.server.coordinator.DataSourceCompactionConfig) ClientCompactionTaskQuery(org.apache.druid.client.indexing.ClientCompactionTaskQuery) TaskStatusPlus(org.apache.druid.indexer.TaskStatusPlus) ArrayList(java.util.ArrayList) List(java.util.List) ImmutableList(com.google.common.collect.ImmutableList) UserCompactionTaskGranularityConfig(org.apache.druid.server.coordinator.UserCompactionTaskGranularityConfig) Test(org.junit.Test)

Aggregations

ArrayList (java.util.ArrayList)2 List (java.util.List)2 ClientCompactionTaskGranularitySpec (org.apache.druid.client.indexing.ClientCompactionTaskGranularitySpec)2 ClientCompactionTaskQuery (org.apache.druid.client.indexing.ClientCompactionTaskQuery)2 TaskPayloadResponse (org.apache.druid.client.indexing.TaskPayloadResponse)2 TaskStatusPlus (org.apache.druid.indexer.TaskStatusPlus)2 DataSourceCompactionConfig (org.apache.druid.server.coordinator.DataSourceCompactionConfig)2 JacksonInject (com.fasterxml.jackson.annotation.JacksonInject)1 JsonCreator (com.fasterxml.jackson.annotation.JsonCreator)1 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)1 VisibleForTesting (com.google.common.annotations.VisibleForTesting)1 ImmutableList (com.google.common.collect.ImmutableList)1 Inject (com.google.inject.Inject)1 HashMap (java.util.HashMap)1 Map (java.util.Map)1 AtomicReference (java.util.concurrent.atomic.AtomicReference)1 Function (java.util.function.Function)1 Collectors (java.util.stream.Collectors)1 Nullable (javax.annotation.Nullable)1 ClientCompactionIOConfig (org.apache.druid.client.indexing.ClientCompactionIOConfig)1