Examples with PartitionsSpec org.apache.druid.indexer.partitions.PartitionsSpec used on opensource projects

Example 1 with PartitionsSpec

use of org.apache.druid.indexer.partitions.PartitionsSpec in project druid by druid-io.

the class CompactSegmentsTest method testRunWithLockedIntervalsNoSkip.

@Test
public void testRunWithLockedIntervalsNoSkip() {
    Mockito.when(COORDINATOR_CONFIG.getCompactionSkipLockedIntervals()).thenReturn(false);
    final TestDruidLeaderClient leaderClient = new TestDruidLeaderClient(JSON_MAPPER);
    leaderClient.start();
    HttpIndexingServiceClient indexingServiceClient = new HttpIndexingServiceClient(JSON_MAPPER, leaderClient);
    // Lock all intervals for all the dataSources
    final String datasource0 = DATA_SOURCE_PREFIX + 0;
    leaderClient.lockedIntervals.computeIfAbsent(datasource0, k -> new ArrayList<>()).add(Intervals.of("2017/2018"));
    final String datasource1 = DATA_SOURCE_PREFIX + 1;
    leaderClient.lockedIntervals.computeIfAbsent(datasource1, k -> new ArrayList<>()).add(Intervals.of("2017/2018"));
    final String datasource2 = DATA_SOURCE_PREFIX + 2;
    leaderClient.lockedIntervals.computeIfAbsent(datasource2, k -> new ArrayList<>()).add(Intervals.of("2017/2018"));
    // Verify that no locked intervals are skipped
    CompactSegments compactSegments = new CompactSegments(COORDINATOR_CONFIG, JSON_MAPPER, indexingServiceClient);
    int maxTaskSlots = partitionsSpec instanceof SingleDimensionPartitionsSpec ? 5 : 3;
    final CoordinatorStats stats = doCompactSegments(compactSegments, createCompactionConfigs(1), maxTaskSlots);
    Assert.assertEquals(3, stats.getGlobalStat(CompactSegments.COMPACTION_TASK_COUNT));
    Assert.assertEquals(3, leaderClient.submittedCompactionTasks.size());
    leaderClient.submittedCompactionTasks.forEach(task -> {
        System.out.println(task.getDataSource() + " : " + task.getIoConfig().getInputSpec().getInterval());
    });
    // Verify that tasks are submitted for the latest interval of each dataSource
    final Map<String, Interval> datasourceToInterval = new HashMap<>();
    leaderClient.submittedCompactionTasks.forEach(task -> datasourceToInterval.put(task.getDataSource(), task.getIoConfig().getInputSpec().getInterval()));
    Assert.assertEquals(Intervals.of("2017-01-09T00:00:00Z/2017-01-09T12:00:00Z"), datasourceToInterval.get(datasource0));
    Assert.assertEquals(Intervals.of("2017-01-09T00:00:00Z/2017-01-09T12:00:00Z"), datasourceToInterval.get(datasource1));
    Assert.assertEquals(Intervals.of("2017-01-09T00:00:00Z/2017-01-09T12:00:00Z"), datasourceToInterval.get(datasource2));
}

Example 2 with PartitionsSpec

use of org.apache.druid.indexer.partitions.PartitionsSpec in project druid by druid-io.

the class NewestSegmentFirstPolicyTest method testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentDimensions.

@Test
public void testIteratorReturnsSegmentsAsSegmentsWasCompactedAndHaveDifferentDimensions() {
    // 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
    // Dimensions=["foo", "bar"] for interval 2017-10-01T00:00:00/2017-10-02T00:00:00,
    // Dimensions=["foo"] for interval 2017-10-02T00:00:00/2017-10-03T00:00:00,
    // Dimensions=null for interval 2017-10-03T00:00:00/2017-10-04T00:00:00 (dimensions was not set during last compaction)
    // and dimensionsSpec=null for interval 2017-10-04T00:00:00/2017-10-05T00:00:00 (dimensionsSpec 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, new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("bar", "foo"))), null, null, indexSpec, null)), new SegmentGenerateSpec(Intervals.of("2017-10-02T00:00:00/2017-10-03T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("foo"))), null, null, indexSpec, null)), new SegmentGenerateSpec(Intervals.of("2017-10-03T00:00:00/2017-10-04T00:00:00"), new Period("P1D"), null, new CompactionState(partitionsSpec, DimensionsSpec.EMPTY, null, null, 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 Dimensions=["foo"]
    CompactionSegmentIterator iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), null, new UserCompactionTaskDimensionsConfig(DimensionsSpec.getDefaultSchemas(ImmutableList.of("foo"))), 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 Dimensions=null
    iterator = policy.reset(ImmutableMap.of(DATA_SOURCE, createCompactionConfig(130000, new Period("P0D"), null, new UserCompactionTaskDimensionsConfig(null), null, null)), ImmutableMap.of(DATA_SOURCE, timeline), Collections.emptyMap());
    // No more
    Assert.assertFalse(iterator.hasNext());
}

Example 3 with PartitionsSpec

use of org.apache.druid.indexer.partitions.PartitionsSpec 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());
}

Example 4 with PartitionsSpec

use of org.apache.druid.indexer.partitions.PartitionsSpec 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());
}

Example 5 with PartitionsSpec

use of org.apache.druid.indexer.partitions.PartitionsSpec 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());
}