Search in sources :

Example 51 with UniformGranularitySpec

use of org.apache.druid.segment.indexing.granularity.UniformGranularitySpec in project druid by druid-io.

the class IndexTaskTest method testOldSegmentNotDropWhenDropFlagTrueSinceIngestionIntervalDoesNotContainsOldSegment.

@Test
public void testOldSegmentNotDropWhenDropFlagTrueSinceIngestionIntervalDoesNotContainsOldSegment() throws Exception {
    File tmpDir = temporaryFolder.newFolder();
    File tmpFile = File.createTempFile("druid", "index", tmpDir);
    try (BufferedWriter writer = Files.newWriter(tmpFile, StandardCharsets.UTF_8)) {
        writer.write("2014-01-01T00:00:10Z,a,1\n");
        writer.write("2014-01-01T01:00:20Z,b,1\n");
        writer.write("2014-01-01T02:00:30Z,c,1\n");
    }
    IndexTask indexTask = new IndexTask(null, null, createDefaultIngestionSpec(jsonMapper, tmpDir, new UniformGranularitySpec(Granularities.YEAR, Granularities.MINUTE, Collections.singletonList(Intervals.of("2014-01-01/2014-01-02"))), null, createTuningConfigWithMaxRowsPerSegment(10, true), false, false), null);
    // Ingest data with YEAR segment granularity
    List<DataSegment> segments = runTask(indexTask).rhs;
    Assert.assertEquals(1, segments.size());
    Set<DataSegment> usedSegmentsBeforeOverwrite = Sets.newHashSet(getSegmentsMetadataManager().iterateAllUsedNonOvershadowedSegmentsForDatasourceInterval(DATASOURCE, Intervals.ETERNITY, true).get());
    Assert.assertEquals(1, usedSegmentsBeforeOverwrite.size());
    for (DataSegment segment : usedSegmentsBeforeOverwrite) {
        Assert.assertTrue(Granularities.YEAR.isAligned(segment.getInterval()));
    }
    indexTask = new IndexTask(null, null, createDefaultIngestionSpec(jsonMapper, tmpDir, new UniformGranularitySpec(Granularities.MINUTE, Granularities.MINUTE, Collections.singletonList(Intervals.of("2014-01-01/2014-01-02"))), null, createTuningConfigWithMaxRowsPerSegment(10, true), false, true), null);
    // Ingest data with overwrite and MINUTE segment granularity
    segments = runTask(indexTask).rhs;
    Assert.assertEquals(3, segments.size());
    Set<DataSegment> usedSegmentsBeforeAfterOverwrite = Sets.newHashSet(getSegmentsMetadataManager().iterateAllUsedNonOvershadowedSegmentsForDatasourceInterval(DATASOURCE, Intervals.ETERNITY, true).get());
    Assert.assertEquals(4, usedSegmentsBeforeAfterOverwrite.size());
    int yearSegmentFound = 0;
    int minuteSegmentFound = 0;
    for (DataSegment segment : usedSegmentsBeforeAfterOverwrite) {
        // and 3 new segments with MINUTE segmentGranularity (from second ingestion)
        if (usedSegmentsBeforeOverwrite.contains(segment)) {
            Assert.assertTrue(Granularities.YEAR.isAligned(segment.getInterval()));
            yearSegmentFound++;
        } else {
            Assert.assertTrue(Granularities.MINUTE.isAligned(segment.getInterval()));
            minuteSegmentFound++;
        }
    }
    Assert.assertEquals(1, yearSegmentFound);
    Assert.assertEquals(3, minuteSegmentFound);
}
Also used : UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) File(java.io.File) DataSegment(org.apache.druid.timeline.DataSegment) BufferedWriter(java.io.BufferedWriter) Test(org.junit.Test)

Example 52 with UniformGranularitySpec

use of org.apache.druid.segment.indexing.granularity.UniformGranularitySpec in project druid by druid-io.

the class IndexTaskTest method testPerfectRollup.

@Test
public void testPerfectRollup() throws Exception {
    File tmpDir = temporaryFolder.newFolder();
    File tmpFile = File.createTempFile("druid", "index", tmpDir);
    populateRollupTestData(tmpFile);
    IndexTask indexTask = new IndexTask(null, null, createDefaultIngestionSpec(jsonMapper, tmpDir, new UniformGranularitySpec(Granularities.DAY, Granularities.DAY, true, null), null, createTuningConfig(3, 2, null, 2L, null, true, true), false, false), null);
    final List<DataSegment> segments = runTask(indexTask).rhs;
    Assert.assertEquals(3, segments.size());
    for (int i = 0; i < 3; i++) {
        final DataSegment segment = segments.get(i);
        final Interval expectedInterval = Intervals.of("2014-01-01T00:00:00.000Z/2014-01-02T00:00:00.000Z");
        Assert.assertEquals(DATASOURCE, segment.getDataSource());
        Assert.assertEquals(expectedInterval, segment.getInterval());
        Assert.assertTrue(segment.getShardSpec().getClass().equals(HashBasedNumberedShardSpec.class));
        Assert.assertEquals(i, segment.getShardSpec().getPartitionNum());
    }
}
Also used : HashBasedNumberedShardSpec(org.apache.druid.timeline.partition.HashBasedNumberedShardSpec) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) File(java.io.File) DataSegment(org.apache.druid.timeline.DataSegment) Interval(org.joda.time.Interval) Test(org.junit.Test)

Example 53 with UniformGranularitySpec

use of org.apache.druid.segment.indexing.granularity.UniformGranularitySpec in project druid by druid-io.

the class IndexTaskTest method testBestEffortRollup.

@Test
public void testBestEffortRollup() throws Exception {
    File tmpDir = temporaryFolder.newFolder();
    File tmpFile = File.createTempFile("druid", "index", tmpDir);
    populateRollupTestData(tmpFile);
    IndexTask indexTask = new IndexTask(null, null, createDefaultIngestionSpec(jsonMapper, tmpDir, new UniformGranularitySpec(Granularities.DAY, Granularities.DAY, true, null), null, createTuningConfig(3, 2, null, 2L, null, false, true), false, false), null);
    final List<DataSegment> segments = runTask(indexTask).rhs;
    Assert.assertEquals(5, segments.size());
    final Interval expectedInterval = Intervals.of("2014-01-01T00:00:00.000Z/2014-01-02T00:00:00.000Z");
    for (int i = 0; i < 5; i++) {
        final DataSegment segment = segments.get(i);
        Assert.assertEquals(DATASOURCE, segment.getDataSource());
        Assert.assertEquals(expectedInterval, segment.getInterval());
        Assert.assertEquals(NumberedShardSpec.class, segment.getShardSpec().getClass());
        Assert.assertEquals(i, segment.getShardSpec().getPartitionNum());
    }
}
Also used : UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) File(java.io.File) DataSegment(org.apache.druid.timeline.DataSegment) Interval(org.joda.time.Interval) Test(org.junit.Test)

Example 54 with UniformGranularitySpec

use of org.apache.druid.segment.indexing.granularity.UniformGranularitySpec in project druid by druid-io.

the class IndexTaskTest method testWaitForSegmentAvailabilityInvalidWaitTimeout.

@Test
public void testWaitForSegmentAvailabilityInvalidWaitTimeout() throws IOException {
    final File tmpDir = temporaryFolder.newFolder();
    TaskToolbox mockToolbox = EasyMock.createMock(TaskToolbox.class);
    List<DataSegment> segmentsToWaitFor = new ArrayList<>();
    segmentsToWaitFor.add(EasyMock.createMock(DataSegment.class));
    IndexTask indexTask = new IndexTask(null, null, createDefaultIngestionSpec(jsonMapper, tmpDir, new UniformGranularitySpec(Granularities.HOUR, Granularities.MINUTE, null), null, createTuningConfigWithMaxRowsPerSegment(2, true), false, false), null);
    EasyMock.replay(mockToolbox);
    Assert.assertFalse(indexTask.waitForSegmentAvailability(mockToolbox, segmentsToWaitFor, -1));
    EasyMock.verify(mockToolbox);
}
Also used : TaskToolbox(org.apache.druid.indexing.common.TaskToolbox) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) ArrayList(java.util.ArrayList) File(java.io.File) DataSegment(org.apache.druid.timeline.DataSegment) Test(org.junit.Test)

Example 55 with UniformGranularitySpec

use of org.apache.druid.segment.indexing.granularity.UniformGranularitySpec in project druid by druid-io.

the class IndexTaskTest method testWaitForSegmentAvailabilityNoSegments.

@Test
public void testWaitForSegmentAvailabilityNoSegments() throws IOException {
    final File tmpDir = temporaryFolder.newFolder();
    TaskToolbox mockToolbox = EasyMock.createMock(TaskToolbox.class);
    List<DataSegment> segmentsToWaitFor = new ArrayList<>();
    IndexTask indexTask = new IndexTask(null, null, createDefaultIngestionSpec(jsonMapper, tmpDir, new UniformGranularitySpec(Granularities.HOUR, Granularities.MINUTE, null), null, createTuningConfigWithMaxRowsPerSegment(2, true), false, false), null);
    EasyMock.replay(mockToolbox);
    Assert.assertTrue(indexTask.waitForSegmentAvailability(mockToolbox, segmentsToWaitFor, 1000));
    EasyMock.verify(mockToolbox);
}
Also used : TaskToolbox(org.apache.druid.indexing.common.TaskToolbox) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) ArrayList(java.util.ArrayList) File(java.io.File) DataSegment(org.apache.druid.timeline.DataSegment) Test(org.junit.Test)

Aggregations

UniformGranularitySpec (org.apache.druid.segment.indexing.granularity.UniformGranularitySpec)91 Test (org.junit.Test)60 DataSchema (org.apache.druid.segment.indexing.DataSchema)49 DimensionsSpec (org.apache.druid.data.input.impl.DimensionsSpec)36 TimestampSpec (org.apache.druid.data.input.impl.TimestampSpec)35 DataSegment (org.apache.druid.timeline.DataSegment)33 File (java.io.File)25 LongSumAggregatorFactory (org.apache.druid.query.aggregation.LongSumAggregatorFactory)24 AggregatorFactory (org.apache.druid.query.aggregation.AggregatorFactory)22 Map (java.util.Map)20 Interval (org.joda.time.Interval)18 CountAggregatorFactory (org.apache.druid.query.aggregation.CountAggregatorFactory)17 ArrayList (java.util.ArrayList)15 HashMap (java.util.HashMap)14 InitializedNullHandlingTest (org.apache.druid.testing.InitializedNullHandlingTest)14 ImmutableMap (com.google.common.collect.ImmutableMap)12 Builder (org.apache.druid.indexing.common.task.CompactionTask.Builder)12 GranularitySpec (org.apache.druid.segment.indexing.granularity.GranularitySpec)12 CompactionState (org.apache.druid.timeline.CompactionState)12 HashBasedNumberedShardSpec (org.apache.druid.timeline.partition.HashBasedNumberedShardSpec)12