Search in sources :

Example 6 with IndexSpec

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

the class NewestSegmentFirstPolicyTest method testIteratorReturnsSegmentsAsCompactionStateChangedWithCompactedStateHasSameSegmentGranularity.

@Test
public void testIteratorReturnsSegmentsAsCompactionStateChangedWithCompactedStateHasSameSegmentGranularity() {
    // Different indexSpec as what is set in the auto compaction config
    IndexSpec newIndexSpec = new IndexSpec(new ConciseBitmapSerdeFactory(), null, null, null);
    Map<String, Object> newIndexSpecMap = mapper.convertValue(newIndexSpec, new TypeReference<Map<String, Object>>() {
    });
    PartitionsSpec partitionsSpec = NewestSegmentFirstIterator.findPartitionsSpecFromConfig(ClientCompactionTaskQueryTuningConfig.from(null, null));
    // Create segments that were compacted (CompactionState != null) and have segmentGranularity=DAY
    final VersionedIntervalTimeline<String, DataSegment> timeline = createTimeline(new SegmentGenerateSpec(Intervals.of("2017-10-02T00:00:00/2017-10-03T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, newIndexSpecMap, null)));
    // Duration of new segmentGranularity is the same as before (P1D)
    final CompactionSegmentIterator iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), new UserCompactionTaskGranularityConfig(new PeriodGranularity(new Period("P1D"), null, DateTimeZone.UTC), null, null))), ImmutableMap.of(DATA_SOURCE, timeline), Collections.emptyMap());
    // We should get all segments in timeline back since indexSpec changed
    Assert.assertTrue(iterator.hasNext());
    List<DataSegment> expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-01T00:00:00/2017-10-03T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    // No more
    Assert.assertFalse(iterator.hasNext());
}
Also used : IndexSpec(org.apache.druid.segment.IndexSpec) PeriodGranularity(org.apache.druid.java.util.common.granularity.PeriodGranularity) ArrayList(java.util.ArrayList) Period(org.joda.time.Period) DataSegment(org.apache.druid.timeline.DataSegment) ConciseBitmapSerdeFactory(org.apache.druid.segment.data.ConciseBitmapSerdeFactory) PartitionsSpec(org.apache.druid.indexer.partitions.PartitionsSpec) CompactionState(org.apache.druid.timeline.CompactionState) UserCompactionTaskGranularityConfig(org.apache.druid.server.coordinator.UserCompactionTaskGranularityConfig) Map(java.util.Map) ImmutableMap(com.google.common.collect.ImmutableMap) Test(org.junit.Test)

Example 7 with IndexSpec

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

the class NewestSegmentFirstPolicyTest method testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentFilter.

@Test
public void testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentFilter() throws Exception {
    NullHandling.initializeForTests();
    // Same indexSpec as what is set in the auto compaction config
    Map<String, Object> indexSpec = mapper.convertValue(new IndexSpec(), new TypeReference<Map<String, Object>>() {
    });
    // Same partitionsSpec as what is set in the auto compaction config
    PartitionsSpec partitionsSpec = NewestSegmentFirstIterator.findPartitionsSpecFromConfig(ClientCompactionTaskQueryTuningConfig.from(null, null));
    // Create segments that were compacted (CompactionState != null) and have
    // filter=SelectorDimFilter("dim1", "foo", null) for interval 2017-10-01T00:00:00/2017-10-02T00:00:00,
    // filter=SelectorDimFilter("dim1", "bar", null) for interval 2017-10-02T00:00:00/2017-10-03T00:00:00,
    // filter=null for interval 2017-10-03T00:00:00/2017-10-04T00:00:00 (filter was not set during last compaction)
    // and transformSpec=null for interval 2017-10-04T00:00:00/2017-10-05T00:00:00 (transformSpec was not set during last compaction)
    final VersionedIntervalTimeline<String, DataSegment> timeline = createTimeline(new SegmentGenerateSpec(Intervals.of("2017-10-01T00:00:00/2017-10-02T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, mapper.readValue(mapper.writeValueAsString(new TransformSpec(new SelectorDimFilter("dim1", "foo", null), null)), new TypeReference<Map<String, Object>>() {
    }), indexSpec, null)), new SegmentGenerateSpec(Intervals.of("2017-10-02T00:00:00/2017-10-03T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, mapper.readValue(mapper.writeValueAsString(new TransformSpec(new SelectorDimFilter("dim1", "bar", null), null)), new TypeReference<Map<String, Object>>() {
    }), indexSpec, null)), new SegmentGenerateSpec(Intervals.of("2017-10-03T00:00:00/2017-10-04T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, mapper.readValue(mapper.writeValueAsString(new TransformSpec(null, null)), new TypeReference<Map<String, Object>>() {
    }), indexSpec, null)), new SegmentGenerateSpec(Intervals.of("2017-10-04T00:00:00/2017-10-05T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, null)));
    // Auto compaction config sets filter=SelectorDimFilter("dim1", "bar", null)
    CompactionSegmentIterator iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), null, null, new UserCompactionTaskTransformConfig(new SelectorDimFilter("dim1", "bar", null)), null)), ImmutableMap.of(DATA_SOURCE, timeline), Collections.emptyMap());
    // We should get interval 2017-10-01T00:00:00/2017-10-02T00:00:00, interval 2017-10-04T00:00:00/2017-10-05T00:00:00, and interval 2017-10-03T00:00:00/2017-10-04T00:00:00.
    Assert.assertTrue(iterator.hasNext());
    List<DataSegment> expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-04T00:00:00/2017-10-05T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    Assert.assertTrue(iterator.hasNext());
    expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-03T00:00:00/2017-10-04T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    Assert.assertTrue(iterator.hasNext());
    expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-01T00:00:00/2017-10-02T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    // No more
    Assert.assertFalse(iterator.hasNext());
    // Auto compaction config sets filter=null
    iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), null, null, new UserCompactionTaskTransformConfig(null), null)), ImmutableMap.of(DATA_SOURCE, timeline), Collections.emptyMap());
    // No more
    Assert.assertFalse(iterator.hasNext());
}
Also used : IndexSpec(org.apache.druid.segment.IndexSpec) ArrayList(java.util.ArrayList) Period(org.joda.time.Period) UserCompactionTaskTransformConfig(org.apache.druid.server.coordinator.UserCompactionTaskTransformConfig) DataSegment(org.apache.druid.timeline.DataSegment) TransformSpec(org.apache.druid.segment.transform.TransformSpec) PartitionsSpec(org.apache.druid.indexer.partitions.PartitionsSpec) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) CompactionState(org.apache.druid.timeline.CompactionState) TypeReference(com.fasterxml.jackson.core.type.TypeReference) Map(java.util.Map) ImmutableMap(com.google.common.collect.ImmutableMap) Test(org.junit.Test)

Example 8 with IndexSpec

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

the class NewestSegmentFirstPolicyTest method testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentOrigin.

@Test
public void testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentOrigin() {
    // Same indexSpec as what is set in the auto compaction config
    Map<String, Object> indexSpec = mapper.convertValue(new IndexSpec(), new TypeReference<Map<String, Object>>() {
    });
    // Same partitionsSpec as what is set in the auto compaction config
    PartitionsSpec partitionsSpec = NewestSegmentFirstIterator.findPartitionsSpecFromConfig(ClientCompactionTaskQueryTuningConfig.from(null, null));
    // Create segments that were compacted (CompactionState != null) and have segmentGranularity=DAY
    final VersionedIntervalTimeline<String, DataSegment> timeline = createTimeline(new SegmentGenerateSpec(Intervals.of("2017-10-02T00:00:00/2017-10-03T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, null)));
    // Duration of new segmentGranularity is the same as before (P1D), but we changed the origin in the autocompaction spec
    final CompactionSegmentIterator iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), new UserCompactionTaskGranularityConfig(new PeriodGranularity(new Period("P1D"), DateTimes.of("2012-01-02T00:05:00.000Z"), DateTimeZone.UTC), null, null))), ImmutableMap.of(DATA_SOURCE, timeline), Collections.emptyMap());
    // We should get all segments in timeline back since skip offset is P0D.
    Assert.assertTrue(iterator.hasNext());
    List<DataSegment> expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-01T00:00:00/2017-10-03T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    // No more
    Assert.assertFalse(iterator.hasNext());
}
Also used : IndexSpec(org.apache.druid.segment.IndexSpec) PeriodGranularity(org.apache.druid.java.util.common.granularity.PeriodGranularity) ArrayList(java.util.ArrayList) Period(org.joda.time.Period) DataSegment(org.apache.druid.timeline.DataSegment) PartitionsSpec(org.apache.druid.indexer.partitions.PartitionsSpec) CompactionState(org.apache.druid.timeline.CompactionState) UserCompactionTaskGranularityConfig(org.apache.druid.server.coordinator.UserCompactionTaskGranularityConfig) Map(java.util.Map) ImmutableMap(com.google.common.collect.ImmutableMap) Test(org.junit.Test)

Example 9 with IndexSpec

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

the class NewestSegmentFirstPolicyTest method testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentQueryGranularity.

@Test
public void testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentQueryGranularity() {
    // Same indexSpec as what is set in the auto compaction config
    Map<String, Object> indexSpec = mapper.convertValue(new IndexSpec(), new TypeReference<Map<String, Object>>() {
    });
    // Same partitionsSpec as what is set in the auto compaction config
    PartitionsSpec partitionsSpec = NewestSegmentFirstIterator.findPartitionsSpecFromConfig(ClientCompactionTaskQueryTuningConfig.from(null, null));
    // Create segments that were compacted (CompactionState != null) and have
    // queryGranularity=DAY for interval 2017-10-01T00:00:00/2017-10-02T00:00:00,
    // queryGranularity=MINUTE for interval 2017-10-02T00:00:00/2017-10-03T00:00:00,
    // and queryGranularity=null for interval 2017-10-03T00:00:00/2017-10-04T00:00:00 (queryGranularity was not set during last compaction)
    final VersionedIntervalTimeline<String, DataSegment> timeline = createTimeline(new SegmentGenerateSpec(Intervals.of("2017-10-01T00:00:00/2017-10-02T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, ImmutableMap.of("queryGranularity", "day"))), new SegmentGenerateSpec(Intervals.of("2017-10-02T00:00:00/2017-10-03T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, ImmutableMap.of("queryGranularity", "minute"))), new SegmentGenerateSpec(Intervals.of("2017-10-03T00:00:00/2017-10-04T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, ImmutableMap.of())));
    // Auto compaction config sets queryGranularity=MINUTE
    final CompactionSegmentIterator iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), new UserCompactionTaskGranularityConfig(null, Granularities.MINUTE, null))), ImmutableMap.of(DATA_SOURCE, timeline), Collections.emptyMap());
    // We should get interval 2017-10-01T00:00:00/2017-10-02T00:00:00 and interval 2017-10-03T00:00:00/2017-10-04T00:00:00.
    Assert.assertTrue(iterator.hasNext());
    List<DataSegment> expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-03T00:00:00/2017-10-04T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    Assert.assertTrue(iterator.hasNext());
    expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-01T00:00:00/2017-10-02T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    // No more
    Assert.assertFalse(iterator.hasNext());
}
Also used : IndexSpec(org.apache.druid.segment.IndexSpec) ArrayList(java.util.ArrayList) Period(org.joda.time.Period) DataSegment(org.apache.druid.timeline.DataSegment) PartitionsSpec(org.apache.druid.indexer.partitions.PartitionsSpec) CompactionState(org.apache.druid.timeline.CompactionState) UserCompactionTaskGranularityConfig(org.apache.druid.server.coordinator.UserCompactionTaskGranularityConfig) Map(java.util.Map) ImmutableMap(com.google.common.collect.ImmutableMap) Test(org.junit.Test)

Example 10 with IndexSpec

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

the class NewestSegmentFirstPolicyTest method testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentRollup.

@Test
public void testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentRollup() {
    // Same indexSpec as what is set in the auto compaction config
    Map<String, Object> indexSpec = mapper.convertValue(new IndexSpec(), new TypeReference<Map<String, Object>>() {
    });
    // Same partitionsSpec as what is set in the auto compaction config
    PartitionsSpec partitionsSpec = NewestSegmentFirstIterator.findPartitionsSpecFromConfig(ClientCompactionTaskQueryTuningConfig.from(null, null));
    // Create segments that were compacted (CompactionState != null) and have
    // rollup=false for interval 2017-10-01T00:00:00/2017-10-02T00:00:00,
    // rollup=true for interval 2017-10-02T00:00:00/2017-10-03T00:00:00,
    // and rollup=null for interval 2017-10-03T00:00:00/2017-10-04T00:00:00 (queryGranularity was not set during last compaction)
    final VersionedIntervalTimeline<String, DataSegment> timeline = createTimeline(new SegmentGenerateSpec(Intervals.of("2017-10-01T00:00:00/2017-10-02T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, ImmutableMap.of("rollup", "false"))), new SegmentGenerateSpec(Intervals.of("2017-10-02T00:00:00/2017-10-03T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, ImmutableMap.of("rollup", "true"))), new SegmentGenerateSpec(Intervals.of("2017-10-03T00:00:00/2017-10-04T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, null, null, null, indexSpec, ImmutableMap.of())));
    // Auto compaction config sets rollup=true
    final CompactionSegmentIterator iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), new UserCompactionTaskGranularityConfig(null, null, true))), ImmutableMap.of(DATA_SOURCE, timeline), Collections.emptyMap());
    // We should get interval 2017-10-01T00:00:00/2017-10-02T00:00:00 and interval 2017-10-03T00:00:00/2017-10-04T00:00:00.
    Assert.assertTrue(iterator.hasNext());
    List<DataSegment> expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-03T00:00:00/2017-10-04T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    Assert.assertTrue(iterator.hasNext());
    expectedSegmentsToCompact = new ArrayList<>(timeline.findNonOvershadowedObjectsInInterval(Intervals.of("2017-10-01T00:00:00/2017-10-02T00:00:00"), Partitions.ONLY_COMPLETE));
    Assert.assertEquals(ImmutableSet.copyOf(expectedSegmentsToCompact), ImmutableSet.copyOf(iterator.next()));
    // No more
    Assert.assertFalse(iterator.hasNext());
}
Also used : IndexSpec(org.apache.druid.segment.IndexSpec) ArrayList(java.util.ArrayList) Period(org.joda.time.Period) DataSegment(org.apache.druid.timeline.DataSegment) PartitionsSpec(org.apache.druid.indexer.partitions.PartitionsSpec) CompactionState(org.apache.druid.timeline.CompactionState) UserCompactionTaskGranularityConfig(org.apache.druid.server.coordinator.UserCompactionTaskGranularityConfig) Map(java.util.Map) ImmutableMap(com.google.common.collect.ImmutableMap) Test(org.junit.Test)

Aggregations

IndexSpec (org.apache.druid.segment.IndexSpec)89 Test (org.junit.Test)59 File (java.io.File)29 Period (org.joda.time.Period)28 RoaringBitmapSerdeFactory (org.apache.druid.segment.data.RoaringBitmapSerdeFactory)25 OnheapIncrementalIndex (org.apache.druid.segment.incremental.OnheapIncrementalIndex)24 ArrayList (java.util.ArrayList)21 Map (java.util.Map)20 DataSegment (org.apache.druid.timeline.DataSegment)20 DynamicPartitionsSpec (org.apache.druid.indexer.partitions.DynamicPartitionsSpec)19 IncrementalIndex (org.apache.druid.segment.incremental.IncrementalIndex)19 CompactionState (org.apache.druid.timeline.CompactionState)16 DimensionsSpec (org.apache.druid.data.input.impl.DimensionsSpec)15 ImmutableMap (com.google.common.collect.ImmutableMap)14 PartitionsSpec (org.apache.druid.indexer.partitions.PartitionsSpec)14 QueryableIndex (org.apache.druid.segment.QueryableIndex)14 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)13 InputRow (org.apache.druid.data.input.InputRow)13 Duration (org.joda.time.Duration)13 DefaultObjectMapper (org.apache.druid.jackson.DefaultObjectMapper)10