Examples with GroupByQueryEngine io.druid.query.groupby.GroupByQueryEngine used on opensource projects

Example 1 with GroupByQueryEngine

use of io.druid.query.groupby.GroupByQueryEngine in project druid by druid-io.

the class IncrementalIndexStorageAdapterTest method testFilterByNull.

@Test
public void testFilterByNull() throws Exception {
    IncrementalIndex index = indexCreator.createIndex();
    index.add(new MapBasedInputRow(new DateTime().minus(1).getMillis(), Lists.newArrayList("billy"), ImmutableMap.<String, Object>of("billy", "hi")));
    index.add(new MapBasedInputRow(new DateTime().minus(1).getMillis(), Lists.newArrayList("sally"), ImmutableMap.<String, Object>of("sally", "bo")));
    GroupByQueryEngine engine = makeGroupByQueryEngine();
    final Sequence<Row> rows = engine.process(GroupByQuery.builder().setDataSource("test").setGranularity(Granularities.ALL).setInterval(new Interval(0, new DateTime().getMillis())).addDimension("billy").addDimension("sally").addAggregator(new LongSumAggregatorFactory("cnt", "cnt")).setDimFilter(DimFilters.dimEquals("sally", (String) null)).build(), new IncrementalIndexStorageAdapter(index));
    final ArrayList<Row> results = Sequences.toList(rows, Lists.<Row>newArrayList());
    Assert.assertEquals(1, results.size());
    MapBasedRow row = (MapBasedRow) results.get(0);
    Assert.assertEquals(ImmutableMap.of("billy", "hi", "cnt", 1L), row.getEvent());
}

Example 2 with GroupByQueryEngine

use of io.druid.query.groupby.GroupByQueryEngine in project druid by druid-io.

the class GroupByTypeInterfaceBenchmark method setup.

@Setup(Level.Trial)
public void setup() throws IOException {
    log.info("SETUP CALLED AT %d", System.currentTimeMillis());
    if (ComplexMetrics.getSerdeForType("hyperUnique") == null) {
        ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde(HyperLogLogHash.getDefault()));
    }
    executorService = Execs.multiThreaded(numProcessingThreads, "GroupByThreadPool[%d]");
    setupQueries();
    String schemaName = "basic";
    schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schemaName);
    stringQuery = SCHEMA_QUERY_MAP.get(schemaName).get("string");
    longFloatQuery = SCHEMA_QUERY_MAP.get(schemaName).get("longFloat");
    longQuery = SCHEMA_QUERY_MAP.get(schemaName).get("long");
    floatQuery = SCHEMA_QUERY_MAP.get(schemaName).get("float");
    final BenchmarkDataGenerator dataGenerator = new BenchmarkDataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED + 1, schemaInfo.getDataInterval(), rowsPerSegment);
    tmpDir = Files.createTempDir();
    log.info("Using temp dir: %s", tmpDir.getAbsolutePath());
    // queryableIndexes   -> numSegments worth of on-disk segments
    // anIncrementalIndex -> the last incremental index
    anIncrementalIndex = null;
    queryableIndexes = new ArrayList<>(numSegments);
    for (int i = 0; i < numSegments; i++) {
        log.info("Generating rows for segment %d/%d", i + 1, numSegments);
        final IncrementalIndex index = makeIncIndex();
        for (int j = 0; j < rowsPerSegment; j++) {
            final InputRow row = dataGenerator.nextRow();
            if (j % 20000 == 0) {
                log.info("%,d/%,d rows generated.", i * rowsPerSegment + j, rowsPerSegment * numSegments);
            }
            index.add(row);
        }
        log.info("%,d/%,d rows generated, persisting segment %d/%d.", (i + 1) * rowsPerSegment, rowsPerSegment * numSegments, i + 1, numSegments);
        final File file = INDEX_MERGER_V9.persist(index, new File(tmpDir, String.valueOf(i)), new IndexSpec());
        queryableIndexes.add(INDEX_IO.loadIndex(file));
        if (i == numSegments - 1) {
            anIncrementalIndex = index;
        } else {
            index.close();
        }
    }
    StupidPool<ByteBuffer> bufferPool = new StupidPool<>("GroupByBenchmark-computeBufferPool", new OffheapBufferGenerator("compute", 250_000_000), 0, Integer.MAX_VALUE);
    // limit of 2 is required since we simulate both historical merge and broker merge in the same process
    BlockingPool<ByteBuffer> mergePool = new BlockingPool<>(new OffheapBufferGenerator("merge", 250_000_000), 2);
    final GroupByQueryConfig config = new GroupByQueryConfig() {

        @Override
        public String getDefaultStrategy() {
            return defaultStrategy;
        }

        @Override
        public int getBufferGrouperInitialBuckets() {
            return initialBuckets;
        }

        @Override
        public long getMaxOnDiskStorage() {
            return 1_000_000_000L;
        }
    };
    config.setSingleThreaded(false);
    config.setMaxIntermediateRows(Integer.MAX_VALUE);
    config.setMaxResults(Integer.MAX_VALUE);
    DruidProcessingConfig druidProcessingConfig = new DruidProcessingConfig() {

        @Override
        public int getNumThreads() {
            // Used by "v2" strategy for concurrencyHint
            return numProcessingThreads;
        }

        @Override
        public String getFormatString() {
            return null;
        }
    };
    final Supplier<GroupByQueryConfig> configSupplier = Suppliers.ofInstance(config);
    final GroupByStrategySelector strategySelector = new GroupByStrategySelector(configSupplier, new GroupByStrategyV1(configSupplier, new GroupByQueryEngine(configSupplier, bufferPool), QueryBenchmarkUtil.NOOP_QUERYWATCHER, bufferPool), new GroupByStrategyV2(druidProcessingConfig, configSupplier, bufferPool, mergePool, new ObjectMapper(new SmileFactory()), QueryBenchmarkUtil.NOOP_QUERYWATCHER));
    factory = new GroupByQueryRunnerFactory(strategySelector, new GroupByQueryQueryToolChest(strategySelector, QueryBenchmarkUtil.NoopIntervalChunkingQueryRunnerDecorator()));
}

Example 3 with GroupByQueryEngine

use of io.druid.query.groupby.GroupByQueryEngine in project druid by druid-io.

the class GroupByBenchmark method setup.

@Setup(Level.Trial)
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + +System.currentTimeMillis());
    if (ComplexMetrics.getSerdeForType("hyperUnique") == null) {
        ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde(HyperLogLogHash.getDefault()));
    }
    executorService = Execs.multiThreaded(numProcessingThreads, "GroupByThreadPool[%d]");
    setupQueries();
    String[] schemaQuery = schemaAndQuery.split("\\.");
    String schemaName = schemaQuery[0];
    String queryName = schemaQuery[1];
    schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schemaName);
    query = SCHEMA_QUERY_MAP.get(schemaName).get(queryName);
    final BenchmarkDataGenerator dataGenerator = new BenchmarkDataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED + 1, schemaInfo.getDataInterval(), rowsPerSegment);
    tmpDir = Files.createTempDir();
    log.info("Using temp dir: %s", tmpDir.getAbsolutePath());
    // queryableIndexes   -> numSegments worth of on-disk segments
    // anIncrementalIndex -> the last incremental index
    anIncrementalIndex = null;
    queryableIndexes = new ArrayList<>(numSegments);
    for (int i = 0; i < numSegments; i++) {
        log.info("Generating rows for segment %d/%d", i + 1, numSegments);
        final IncrementalIndex index = makeIncIndex(schemaInfo.isWithRollup());
        for (int j = 0; j < rowsPerSegment; j++) {
            final InputRow row = dataGenerator.nextRow();
            if (j % 20000 == 0) {
                log.info("%,d/%,d rows generated.", i * rowsPerSegment + j, rowsPerSegment * numSegments);
            }
            index.add(row);
        }
        log.info("%,d/%,d rows generated, persisting segment %d/%d.", (i + 1) * rowsPerSegment, rowsPerSegment * numSegments, i + 1, numSegments);
        final File file = INDEX_MERGER_V9.persist(index, new File(tmpDir, String.valueOf(i)), new IndexSpec());
        queryableIndexes.add(INDEX_IO.loadIndex(file));
        if (i == numSegments - 1) {
            anIncrementalIndex = index;
        } else {
            index.close();
        }
    }
    StupidPool<ByteBuffer> bufferPool = new StupidPool<>("GroupByBenchmark-computeBufferPool", new OffheapBufferGenerator("compute", 250_000_000), 0, Integer.MAX_VALUE);
    // limit of 2 is required since we simulate both historical merge and broker merge in the same process
    BlockingPool<ByteBuffer> mergePool = new BlockingPool<>(new OffheapBufferGenerator("merge", 250_000_000), 2);
    final GroupByQueryConfig config = new GroupByQueryConfig() {

        @Override
        public String getDefaultStrategy() {
            return defaultStrategy;
        }

        @Override
        public int getBufferGrouperInitialBuckets() {
            return initialBuckets;
        }

        @Override
        public long getMaxOnDiskStorage() {
            return 1_000_000_000L;
        }
    };
    config.setSingleThreaded(false);
    config.setMaxIntermediateRows(Integer.MAX_VALUE);
    config.setMaxResults(Integer.MAX_VALUE);
    DruidProcessingConfig druidProcessingConfig = new DruidProcessingConfig() {

        @Override
        public int getNumThreads() {
            // Used by "v2" strategy for concurrencyHint
            return numProcessingThreads;
        }

        @Override
        public String getFormatString() {
            return null;
        }
    };
    final Supplier<GroupByQueryConfig> configSupplier = Suppliers.ofInstance(config);
    final GroupByStrategySelector strategySelector = new GroupByStrategySelector(configSupplier, new GroupByStrategyV1(configSupplier, new GroupByQueryEngine(configSupplier, bufferPool), QueryBenchmarkUtil.NOOP_QUERYWATCHER, bufferPool), new GroupByStrategyV2(druidProcessingConfig, configSupplier, bufferPool, mergePool, new ObjectMapper(new SmileFactory()), QueryBenchmarkUtil.NOOP_QUERYWATCHER));
    factory = new GroupByQueryRunnerFactory(strategySelector, new GroupByQueryQueryToolChest(strategySelector, QueryBenchmarkUtil.NoopIntervalChunkingQueryRunnerDecorator()));
}

Example 4 with GroupByQueryEngine

use of io.druid.query.groupby.GroupByQueryEngine in project druid by druid-io.

the class IncrementalIndexStorageAdapterTest method testObjectColumnSelectorOnVaryingColumnSchema.

@Test
public void testObjectColumnSelectorOnVaryingColumnSchema() throws Exception {
    IncrementalIndex index = indexCreator.createIndex();
    index.add(new MapBasedInputRow(new DateTime("2014-09-01T00:00:00"), Lists.newArrayList("billy"), ImmutableMap.<String, Object>of("billy", "hi")));
    index.add(new MapBasedInputRow(new DateTime("2014-09-01T01:00:00"), Lists.newArrayList("billy", "sally"), ImmutableMap.<String, Object>of("billy", "hip", "sally", "hop")));
    GroupByQueryEngine engine = makeGroupByQueryEngine();
    final Sequence<Row> rows = engine.process(GroupByQuery.builder().setDataSource("test").setGranularity(Granularities.ALL).setInterval(new Interval(0, new DateTime().getMillis())).addDimension("billy").addDimension("sally").addAggregator(new LongSumAggregatorFactory("cnt", "cnt")).addAggregator(new JavaScriptAggregatorFactory("fieldLength", Arrays.asList("sally", "billy"), "function(current, s, b) { return current + (s == null ? 0 : s.length) + (b == null ? 0 : b.length); }", "function() { return 0; }", "function(a,b) { return a + b; }", JavaScriptConfig.getEnabledInstance())).build(), new IncrementalIndexStorageAdapter(index));
    final ArrayList<Row> results = Sequences.toList(rows, Lists.<Row>newArrayList());
    Assert.assertEquals(2, results.size());
    MapBasedRow row = (MapBasedRow) results.get(0);
    Assert.assertEquals(ImmutableMap.of("billy", "hi", "cnt", 1L, "fieldLength", 2.0), row.getEvent());
    row = (MapBasedRow) results.get(1);
    Assert.assertEquals(ImmutableMap.of("billy", "hip", "sally", "hop", "cnt", 1L, "fieldLength", 6.0), row.getEvent());
}

Example 5 with GroupByQueryEngine

use of io.druid.query.groupby.GroupByQueryEngine in project druid by druid-io.

the class IncrementalIndexStorageAdapterTest method testSanity.

@Test
public void testSanity() throws Exception {
    IncrementalIndex index = indexCreator.createIndex();
    index.add(new MapBasedInputRow(new DateTime().minus(1).getMillis(), Lists.newArrayList("billy"), ImmutableMap.<String, Object>of("billy", "hi")));
    index.add(new MapBasedInputRow(new DateTime().minus(1).getMillis(), Lists.newArrayList("sally"), ImmutableMap.<String, Object>of("sally", "bo")));
    GroupByQueryEngine engine = makeGroupByQueryEngine();
    final Sequence<Row> rows = engine.process(GroupByQuery.builder().setDataSource("test").setGranularity(Granularities.ALL).setInterval(new Interval(0, new DateTime().getMillis())).addDimension("billy").addDimension("sally").addAggregator(new LongSumAggregatorFactory("cnt", "cnt")).build(), new IncrementalIndexStorageAdapter(index));
    final ArrayList<Row> results = Sequences.toList(rows, Lists.<Row>newArrayList());
    Assert.assertEquals(2, results.size());
    MapBasedRow row = (MapBasedRow) results.get(0);
    Assert.assertEquals(ImmutableMap.of("sally", "bo", "cnt", 1L), row.getEvent());
    row = (MapBasedRow) results.get(1);
    Assert.assertEquals(ImmutableMap.of("billy", "hi", "cnt", 1L), row.getEvent());
}