Examples with SegmentsSplitHintSpec org.apache.druid.data.input.SegmentsSplitHintSpec used on opensource projects

Example 1 with SegmentsSplitHintSpec

use of org.apache.druid.data.input.SegmentsSplitHintSpec in project druid by druid-io.

the class ClientCompactionTaskQuerySerdeTest method testCompactionTaskToClientCompactionTaskQuery.

@Test
public void testCompactionTaskToClientCompactionTaskQuery() throws IOException {
    final ObjectMapper mapper = setupInjectablesInObjectMapper(new DefaultObjectMapper());
    final CompactionTask.Builder builder = new CompactionTask.Builder("datasource", new SegmentCacheManagerFactory(mapper), new RetryPolicyFactory(new RetryPolicyConfig()));
    final CompactionTask task = builder.inputSpec(new CompactionIntervalSpec(Intervals.of("2019/2020"), "testSha256OfSortedSegmentIds"), true).tuningConfig(new ParallelIndexTuningConfig(null, null, null, 40000, 2000L, null, null, null, new SegmentsSplitHintSpec(new HumanReadableBytes(100000L), 10), new DynamicPartitionsSpec(100, 30000L), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.LZF, LongEncodingStrategy.LONGS), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.UNCOMPRESSED, LongEncodingStrategy.AUTO), 2, null, null, 1000L, TmpFileSegmentWriteOutMediumFactory.instance(), null, 100, 5, 1000L, new Duration(3000L), 7, 1000, 100, null, null, null, null, null, null)).granularitySpec(new ClientCompactionTaskGranularitySpec(Granularities.DAY, Granularities.HOUR, true)).dimensionsSpec(DimensionsSpec.builder().setDimensions(DimensionsSpec.getDefaultSchemas(ImmutableList.of("ts", "dim"))).setDimensionExclusions(ImmutableList.of("__time", "val")).build()).metricsSpec(new AggregatorFactory[] { new CountAggregatorFactory("cnt") }).transformSpec(new ClientCompactionTaskTransformSpec(new SelectorDimFilter("dim1", "foo", null))).build();
    final ClientCompactionTaskQuery expected = new ClientCompactionTaskQuery(task.getId(), "datasource", new ClientCompactionIOConfig(new ClientCompactionIntervalSpec(Intervals.of("2019/2020"), "testSha256OfSortedSegmentIds"), true), new ClientCompactionTaskQueryTuningConfig(100, 40000, 2000L, 30000L, new SegmentsSplitHintSpec(new HumanReadableBytes(100000L), 10), new DynamicPartitionsSpec(100, 30000L), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.LZF, LongEncodingStrategy.LONGS), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.UNCOMPRESSED, LongEncodingStrategy.AUTO), 2, 1000L, TmpFileSegmentWriteOutMediumFactory.instance(), 100, 5, 1000L, new Duration(3000L), 7, 1000, 100), new ClientCompactionTaskGranularitySpec(Granularities.DAY, Granularities.HOUR, true), new ClientCompactionTaskDimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("ts", "dim"))), new AggregatorFactory[] { new CountAggregatorFactory("cnt") }, new ClientCompactionTaskTransformSpec(new SelectorDimFilter("dim1", "foo", null)), new HashMap<>());
    final byte[] json = mapper.writeValueAsBytes(task);
    final ClientCompactionTaskQuery actual = (ClientCompactionTaskQuery) mapper.readValue(json, ClientTaskQuery.class);
    Assert.assertEquals(expected, actual);
}

Example 2 with SegmentsSplitHintSpec

use of org.apache.druid.data.input.SegmentsSplitHintSpec in project druid by druid-io.

the class DruidInputSource method createSplits.

public static Iterator<InputSplit<List<WindowedSegmentId>>> createSplits(CoordinatorClient coordinatorClient, RetryPolicyFactory retryPolicyFactory, String dataSource, Interval interval, SplitHintSpec splitHintSpec) {
    final SplitHintSpec convertedSplitHintSpec;
    if (splitHintSpec instanceof SegmentsSplitHintSpec) {
        final SegmentsSplitHintSpec segmentsSplitHintSpec = (SegmentsSplitHintSpec) splitHintSpec;
        convertedSplitHintSpec = new MaxSizeSplitHintSpec(segmentsSplitHintSpec.getMaxInputSegmentBytesPerTask(), segmentsSplitHintSpec.getMaxNumSegments());
    } else {
        convertedSplitHintSpec = splitHintSpec;
    }
    final List<TimelineObjectHolder<String, DataSegment>> timelineSegments = getTimelineForInterval(coordinatorClient, retryPolicyFactory, dataSource, interval);
    final Map<WindowedSegmentId, Long> segmentIdToSize = createWindowedSegmentIdFromTimeline(timelineSegments);
    // noinspection ConstantConditions
    return Iterators.transform(convertedSplitHintSpec.split(// the same input split.
    segmentIdToSize.keySet().iterator(), segmentId -> new InputFileAttribute(Preconditions.checkNotNull(segmentIdToSize.get(segmentId), "segment size for [%s]", segmentId))), InputSplit::new);
}

Example 3 with SegmentsSplitHintSpec

use of org.apache.druid.data.input.SegmentsSplitHintSpec in project druid by druid-io.

the class ClientCompactionTaskQuerySerdeTest method testClientCompactionTaskQueryToCompactionTask.

@Test
public void testClientCompactionTaskQueryToCompactionTask() throws IOException {
    final ObjectMapper mapper = setupInjectablesInObjectMapper(new DefaultObjectMapper());
    final ClientCompactionTaskQuery query = new ClientCompactionTaskQuery("id", "datasource", new ClientCompactionIOConfig(new ClientCompactionIntervalSpec(Intervals.of("2019/2020"), "testSha256OfSortedSegmentIds"), true), new ClientCompactionTaskQueryTuningConfig(null, 40000, 2000L, null, new SegmentsSplitHintSpec(new HumanReadableBytes(100000L), 10), new DynamicPartitionsSpec(100, 30000L), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.LZF, LongEncodingStrategy.LONGS), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.UNCOMPRESSED, LongEncodingStrategy.AUTO), 2, 1000L, TmpFileSegmentWriteOutMediumFactory.instance(), 100, 5, 1000L, new Duration(3000L), 7, 1000, 100), new ClientCompactionTaskGranularitySpec(Granularities.DAY, Granularities.HOUR, true), new ClientCompactionTaskDimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("ts", "dim"))), new AggregatorFactory[] { new CountAggregatorFactory("cnt") }, new ClientCompactionTaskTransformSpec(new SelectorDimFilter("dim1", "foo", null)), ImmutableMap.of("key", "value"));
    final byte[] json = mapper.writeValueAsBytes(query);
    final CompactionTask task = (CompactionTask) mapper.readValue(json, Task.class);
    Assert.assertEquals(query.getId(), task.getId());
    Assert.assertEquals(query.getDataSource(), task.getDataSource());
    Assert.assertTrue(task.getIoConfig().getInputSpec() instanceof CompactionIntervalSpec);
    Assert.assertEquals(query.getIoConfig().getInputSpec().getInterval(), ((CompactionIntervalSpec) task.getIoConfig().getInputSpec()).getInterval());
    Assert.assertEquals(query.getIoConfig().getInputSpec().getSha256OfSortedSegmentIds(), ((CompactionIntervalSpec) task.getIoConfig().getInputSpec()).getSha256OfSortedSegmentIds());
    Assert.assertEquals(query.getTuningConfig().getMaxRowsInMemory().intValue(), task.getTuningConfig().getMaxRowsInMemory());
    Assert.assertEquals(query.getTuningConfig().getMaxBytesInMemory().longValue(), task.getTuningConfig().getMaxBytesInMemory());
    Assert.assertEquals(query.getTuningConfig().getSplitHintSpec(), task.getTuningConfig().getSplitHintSpec());
    Assert.assertEquals(query.getTuningConfig().getPartitionsSpec(), task.getTuningConfig().getPartitionsSpec());
    Assert.assertEquals(query.getTuningConfig().getIndexSpec(), task.getTuningConfig().getIndexSpec());
    Assert.assertEquals(query.getTuningConfig().getIndexSpecForIntermediatePersists(), task.getTuningConfig().getIndexSpecForIntermediatePersists());
    Assert.assertEquals(query.getTuningConfig().getPushTimeout().longValue(), task.getTuningConfig().getPushTimeout());
    Assert.assertEquals(query.getTuningConfig().getSegmentWriteOutMediumFactory(), task.getTuningConfig().getSegmentWriteOutMediumFactory());
    Assert.assertEquals(query.getTuningConfig().getMaxNumConcurrentSubTasks().intValue(), task.getTuningConfig().getMaxNumConcurrentSubTasks());
    Assert.assertEquals(query.getTuningConfig().getMaxRetry().intValue(), task.getTuningConfig().getMaxRetry());
    Assert.assertEquals(query.getTuningConfig().getTaskStatusCheckPeriodMs().longValue(), task.getTuningConfig().getTaskStatusCheckPeriodMs());
    Assert.assertEquals(query.getTuningConfig().getChatHandlerTimeout(), task.getTuningConfig().getChatHandlerTimeout());
    Assert.assertEquals(query.getTuningConfig().getMaxNumSegmentsToMerge().intValue(), task.getTuningConfig().getMaxNumSegmentsToMerge());
    Assert.assertEquals(query.getTuningConfig().getTotalNumMergeTasks().intValue(), task.getTuningConfig().getTotalNumMergeTasks());
    Assert.assertEquals(query.getGranularitySpec(), task.getGranularitySpec());
    Assert.assertEquals(query.getGranularitySpec().getQueryGranularity(), task.getGranularitySpec().getQueryGranularity());
    Assert.assertEquals(query.getGranularitySpec().getSegmentGranularity(), task.getGranularitySpec().getSegmentGranularity());
    Assert.assertEquals(query.getGranularitySpec().isRollup(), task.getGranularitySpec().isRollup());
    Assert.assertEquals(query.getIoConfig().isDropExisting(), task.getIoConfig().isDropExisting());
    Assert.assertEquals(query.getContext(), task.getContext());
    Assert.assertEquals(query.getDimensionsSpec().getDimensions(), task.getDimensionsSpec().getDimensions());
    Assert.assertEquals(query.getTransformSpec().getFilter(), task.getTransformSpec().getFilter());
    Assert.assertArrayEquals(query.getMetricsSpec(), task.getMetricsSpec());
}

Example 4 with SegmentsSplitHintSpec

use of org.apache.druid.data.input.SegmentsSplitHintSpec in project druid by druid-io.

the class UserCompactionTaskQueryTuningConfigTest method testSerde.

@Test
public void testSerde() throws IOException {
    final UserCompactionTaskQueryTuningConfig tuningConfig = new UserCompactionTaskQueryTuningConfig(40000, 2000L, null, new SegmentsSplitHintSpec(new HumanReadableBytes(42L), null), new DynamicPartitionsSpec(1000, 20000L), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.LZF, LongEncodingStrategy.LONGS), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.UNCOMPRESSED, LongEncodingStrategy.AUTO), 2, 1000L, TmpFileSegmentWriteOutMediumFactory.instance(), 100, 5, 1000L, new Duration(3000L), 7, 1000, 100);
    final String json = OBJECT_MAPPER.writeValueAsString(tuningConfig);
    final UserCompactionTaskQueryTuningConfig fromJson = OBJECT_MAPPER.readValue(json, UserCompactionTaskQueryTuningConfig.class);
    Assert.assertEquals(tuningConfig, fromJson);
}

Example 5 with SegmentsSplitHintSpec

use of org.apache.druid.data.input.SegmentsSplitHintSpec in project druid by druid-io.

the class DataSourceCompactionConfigTest method testSerdeUserCompactionTuningConfig.

@Test
public void testSerdeUserCompactionTuningConfig() throws IOException {
    final UserCompactionTaskQueryTuningConfig tuningConfig = new UserCompactionTaskQueryTuningConfig(40000, 2000L, null, new SegmentsSplitHintSpec(new HumanReadableBytes(100000L), null), new DynamicPartitionsSpec(1000, 20000L), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.LZF, LongEncodingStrategy.LONGS), new IndexSpec(new DefaultBitmapSerdeFactory(), CompressionStrategy.LZ4, CompressionStrategy.UNCOMPRESSED, LongEncodingStrategy.AUTO), 2, 1000L, TmpFileSegmentWriteOutMediumFactory.instance(), 100, 5, 1000L, new Duration(3000L), 7, 1000, 100);
    final String json = OBJECT_MAPPER.writeValueAsString(tuningConfig);
    final UserCompactionTaskQueryTuningConfig fromJson = OBJECT_MAPPER.readValue(json, UserCompactionTaskQueryTuningConfig.class);
    Assert.assertEquals(tuningConfig, fromJson);
}