Examples with IncrementalIndexStorageAdapter io.druid.segment.incremental.IncrementalIndexStorageAdapter used on opensource projects

Example 1 with IncrementalIndexStorageAdapter

use of io.druid.segment.incremental.IncrementalIndexStorageAdapter in project druid by druid-io.

the class GroupByStrategyV1 method processSubqueryResult.

@Override
public Sequence<Row> processSubqueryResult(GroupByQuery subquery, GroupByQuery query, GroupByQueryResource resource, Sequence<Row> subqueryResult) {
    final Set<AggregatorFactory> aggs = Sets.newHashSet();
    // Nested group-bys work by first running the inner query and then materializing the results in an incremental
    // index which the outer query is then run against. To build the incremental index, we use the fieldNames from
    // the aggregators for the outer query to define the column names so that the index will match the query. If
    // there are multiple types of aggregators in the outer query referencing the same fieldName, we will try to build
    // multiple columns of the same name using different aggregator types and will fail. Here, we permit multiple
    // aggregators of the same type referencing the same fieldName (and skip creating identical columns for the
    // subsequent ones) and return an error if the aggregator types are different.
    final Set<String> dimensionNames = Sets.newHashSet();
    for (DimensionSpec dimension : subquery.getDimensions()) {
        dimensionNames.add(dimension.getOutputName());
    }
    for (AggregatorFactory aggregatorFactory : query.getAggregatorSpecs()) {
        for (final AggregatorFactory transferAgg : aggregatorFactory.getRequiredColumns()) {
            if (dimensionNames.contains(transferAgg.getName())) {
                // doesn't have this problem.
                continue;
            }
            if (Iterables.any(aggs, new Predicate<AggregatorFactory>() {

                @Override
                public boolean apply(AggregatorFactory agg) {
                    return agg.getName().equals(transferAgg.getName()) && !agg.equals(transferAgg);
                }
            })) {
                throw new IAE("Inner aggregator can currently only be referenced by a single type of outer aggregator" + " for '%s'", transferAgg.getName());
            }
            aggs.add(transferAgg);
        }
    }
    // We need the inner incremental index to have all the columns required by the outer query
    final GroupByQuery innerQuery = new GroupByQuery.Builder(subquery).setAggregatorSpecs(Lists.newArrayList(aggs)).setInterval(subquery.getIntervals()).setPostAggregatorSpecs(Lists.<PostAggregator>newArrayList()).build();
    final GroupByQuery outerQuery = new GroupByQuery.Builder(query).setLimitSpec(query.getLimitSpec().merge(subquery.getLimitSpec())).build();
    final IncrementalIndex innerQueryResultIndex = GroupByQueryHelper.makeIncrementalIndex(innerQuery.withOverriddenContext(ImmutableMap.<String, Object>of(GroupByQueryHelper.CTX_KEY_SORT_RESULTS, true)), configSupplier.get(), bufferPool, subqueryResult, false);
    //Outer query might have multiple intervals, but they are expected to be non-overlapping and sorted which
    //is ensured by QuerySegmentSpec.
    //GroupByQueryEngine can only process one interval at a time, so we need to call it once per interval
    //and concatenate the results.
    final IncrementalIndex outerQueryResultIndex = GroupByQueryHelper.makeIncrementalIndex(outerQuery, configSupplier.get(), bufferPool, Sequences.concat(Sequences.map(Sequences.simple(outerQuery.getIntervals()), new Function<Interval, Sequence<Row>>() {

        @Override
        public Sequence<Row> apply(Interval interval) {
            return process(outerQuery.withQuerySegmentSpec(new MultipleIntervalSegmentSpec(ImmutableList.of(interval))), new IncrementalIndexStorageAdapter(innerQueryResultIndex));
        }
    })), true);
    innerQueryResultIndex.close();
    return Sequences.withBaggage(outerQuery.applyLimit(GroupByQueryHelper.postAggregate(query, outerQueryResultIndex)), outerQueryResultIndex);
}

Example 2 with IncrementalIndexStorageAdapter

use of io.druid.segment.incremental.IncrementalIndexStorageAdapter in project druid by druid-io.

the class IncrementalIndexReadBenchmark method read.

@Benchmark
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.MICROSECONDS)
public void read(Blackhole blackhole) throws Exception {
    IncrementalIndexStorageAdapter sa = new IncrementalIndexStorageAdapter(incIndex);
    Sequence<Cursor> cursors = makeCursors(sa, null);
    Cursor cursor = Sequences.toList(Sequences.limit(cursors, 1), Lists.<Cursor>newArrayList()).get(0);
    List<DimensionSelector> selectors = new ArrayList<>();
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimSequential", null)));
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimZipf", null)));
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimUniform", null)));
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimSequentialHalfNull", null)));
    cursor.reset();
    while (!cursor.isDone()) {
        for (DimensionSelector selector : selectors) {
            IndexedInts row = selector.getRow();
            blackhole.consume(selector.lookupName(row.get(0)));
        }
        cursor.advance();
    }
}

Example 3 with IncrementalIndexStorageAdapter

use of io.druid.segment.incremental.IncrementalIndexStorageAdapter in project druid by druid-io.

the class IncrementalIndexReadBenchmark method readWithFilters.

@Benchmark
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.MICROSECONDS)
public void readWithFilters(Blackhole blackhole) throws Exception {
    DimFilter filter = new OrDimFilter(Arrays.asList(new BoundDimFilter("dimSequential", "-1", "-1", true, true, null, null, StringComparators.ALPHANUMERIC), new JavaScriptDimFilter("dimSequential", "function(x) { return false }", null, JavaScriptConfig.getEnabledInstance()), new RegexDimFilter("dimSequential", "X", null), new SearchQueryDimFilter("dimSequential", new ContainsSearchQuerySpec("X", false), null), new InDimFilter("dimSequential", Arrays.asList("X"), null)));
    IncrementalIndexStorageAdapter sa = new IncrementalIndexStorageAdapter(incIndex);
    Sequence<Cursor> cursors = makeCursors(sa, filter);
    Cursor cursor = Sequences.toList(Sequences.limit(cursors, 1), Lists.<Cursor>newArrayList()).get(0);
    List<DimensionSelector> selectors = new ArrayList<>();
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimSequential", null)));
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimZipf", null)));
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimUniform", null)));
    selectors.add(cursor.makeDimensionSelector(new DefaultDimensionSpec("dimSequentialHalfNull", null)));
    cursor.reset();
    while (!cursor.isDone()) {
        for (DimensionSelector selector : selectors) {
            IndexedInts row = selector.getRow();
            blackhole.consume(selector.lookupName(row.get(0)));
        }
        cursor.advance();
    }
}

Example 4 with IncrementalIndexStorageAdapter

use of io.druid.segment.incremental.IncrementalIndexStorageAdapter in project druid by druid-io.

the class BaseFilterTest method makeConstructors.

public static Collection<Object[]> makeConstructors() {
    final List<Object[]> constructors = Lists.newArrayList();
    final Map<String, BitmapSerdeFactory> bitmapSerdeFactories = ImmutableMap.<String, BitmapSerdeFactory>of("concise", new ConciseBitmapSerdeFactory(), "roaring", new RoaringBitmapSerdeFactory(true));
    final Map<String, IndexMerger> indexMergers = ImmutableMap.<String, IndexMerger>of("IndexMerger", TestHelper.getTestIndexMerger(), "IndexMergerV9", TestHelper.getTestIndexMergerV9());
    final Map<String, Function<IndexBuilder, Pair<StorageAdapter, Closeable>>> finishers = ImmutableMap.of("incremental", new Function<IndexBuilder, Pair<StorageAdapter, Closeable>>() {

        @Override
        public Pair<StorageAdapter, Closeable> apply(IndexBuilder input) {
            final IncrementalIndex index = input.buildIncrementalIndex();
            return Pair.<StorageAdapter, Closeable>of(new IncrementalIndexStorageAdapter(index), new Closeable() {

                @Override
                public void close() throws IOException {
                    index.close();
                }
            });
        }
    }, "mmapped", new Function<IndexBuilder, Pair<StorageAdapter, Closeable>>() {

        @Override
        public Pair<StorageAdapter, Closeable> apply(IndexBuilder input) {
            final QueryableIndex index = input.buildMMappedIndex();
            return Pair.<StorageAdapter, Closeable>of(new QueryableIndexStorageAdapter(index), new Closeable() {

                @Override
                public void close() throws IOException {
                    index.close();
                }
            });
        }
    }, "mmappedMerged", new Function<IndexBuilder, Pair<StorageAdapter, Closeable>>() {

        @Override
        public Pair<StorageAdapter, Closeable> apply(IndexBuilder input) {
            final QueryableIndex index = input.buildMMappedMergedIndex();
            return Pair.<StorageAdapter, Closeable>of(new QueryableIndexStorageAdapter(index), new Closeable() {

                @Override
                public void close() throws IOException {
                    index.close();
                }
            });
        }
    });
    for (Map.Entry<String, BitmapSerdeFactory> bitmapSerdeFactoryEntry : bitmapSerdeFactories.entrySet()) {
        for (Map.Entry<String, IndexMerger> indexMergerEntry : indexMergers.entrySet()) {
            for (Map.Entry<String, Function<IndexBuilder, Pair<StorageAdapter, Closeable>>> finisherEntry : finishers.entrySet()) {
                for (boolean cnf : ImmutableList.of(false, true)) {
                    for (boolean optimize : ImmutableList.of(false, true)) {
                        final String testName = String.format("bitmaps[%s], indexMerger[%s], finisher[%s], optimize[%s]", bitmapSerdeFactoryEntry.getKey(), indexMergerEntry.getKey(), finisherEntry.getKey(), optimize);
                        final IndexBuilder indexBuilder = IndexBuilder.create().indexSpec(new IndexSpec(bitmapSerdeFactoryEntry.getValue(), null, null, null)).indexMerger(indexMergerEntry.getValue());
                        constructors.add(new Object[] { testName, indexBuilder, finisherEntry.getValue(), cnf, optimize });
                    }
                }
            }
        }
    }
    return constructors;
}

Example 5 with IncrementalIndexStorageAdapter

use of io.druid.segment.incremental.IncrementalIndexStorageAdapter in project druid by druid-io.

the class DistinctCountTimeseriesQueryTest method testTopNWithDistinctCountAgg.

@Test
public void testTopNWithDistinctCountAgg() throws Exception {
    TimeseriesQueryEngine engine = new TimeseriesQueryEngine();
    IncrementalIndex index = new OnheapIncrementalIndex(0, Granularities.SECOND, new AggregatorFactory[] { new CountAggregatorFactory("cnt") }, 1000);
    String visitor_id = "visitor_id";
    String client_type = "client_type";
    DateTime time = new DateTime("2016-03-04T00:00:00.000Z");
    long timestamp = time.getMillis();
    index.add(new MapBasedInputRow(timestamp, Lists.newArrayList(visitor_id, client_type), ImmutableMap.<String, Object>of(visitor_id, "0", client_type, "iphone")));
    index.add(new MapBasedInputRow(timestamp, Lists.newArrayList(visitor_id, client_type), ImmutableMap.<String, Object>of(visitor_id, "1", client_type, "iphone")));
    index.add(new MapBasedInputRow(timestamp, Lists.newArrayList(visitor_id, client_type), ImmutableMap.<String, Object>of(visitor_id, "2", client_type, "android")));
    TimeseriesQuery query = Druids.newTimeseriesQueryBuilder().dataSource(QueryRunnerTestHelper.dataSource).granularity(QueryRunnerTestHelper.allGran).intervals(QueryRunnerTestHelper.fullOnInterval).aggregators(Lists.newArrayList(QueryRunnerTestHelper.rowsCount, new DistinctCountAggregatorFactory("UV", visitor_id, null))).build();
    final Iterable<Result<TimeseriesResultValue>> results = Sequences.toList(engine.process(query, new IncrementalIndexStorageAdapter(index)), Lists.<Result<TimeseriesResultValue>>newLinkedList());
    List<Result<TimeseriesResultValue>> expectedResults = Arrays.asList(new Result<>(time, new TimeseriesResultValue(ImmutableMap.<String, Object>of("UV", 3, "rows", 3L))));
    TestHelper.assertExpectedResults(expectedResults, results);
}