Examples with DataGenerator org.apache.druid.segment.generator.DataGenerator used on opensource projects

Example 11 with DataGenerator

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

the class GroupByBenchmark method setup.

/**
 * Setup everything common for benchmarking both the incremental-index and the queriable-index.
 */
@Setup(Level.Trial)
public void setup() {
    log.info("SETUP CALLED AT " + +System.currentTimeMillis());
    ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde());
    setupQueries();
    String[] schemaQuery = schemaAndQuery.split("\\.");
    String schemaName = schemaQuery[0];
    String queryName = schemaQuery[1];
    schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get(schemaName);
    query = SCHEMA_QUERY_MAP.get(schemaName).get(queryName);
    generator = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
    NonBlockingPool<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 DefaultBlockingPool<>(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), new GroupByStrategyV2(druidProcessingConfig, configSupplier, bufferPool, mergePool, new ObjectMapper(new SmileFactory()), QueryBenchmarkUtil.NOOP_QUERYWATCHER));
    factory = new GroupByQueryRunnerFactory(strategySelector, new GroupByQueryQueryToolChest(strategySelector));
}

Example 12 with DataGenerator

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

the class TopNTypeInterfaceBenchmark method setup.

@Setup
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + System.currentTimeMillis());
    ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde());
    setupQueries();
    schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get("basic");
    queryBuilder = SCHEMA_QUERY_MAP.get("basic").get("string");
    queryBuilder.threshold(threshold);
    stringQuery = queryBuilder.build();
    TopNQueryBuilder longBuilder = SCHEMA_QUERY_MAP.get("basic").get("long");
    longBuilder.threshold(threshold);
    longQuery = longBuilder.build();
    TopNQueryBuilder floatBuilder = SCHEMA_QUERY_MAP.get("basic").get("float");
    floatBuilder.threshold(threshold);
    floatQuery = floatBuilder.build();
    incIndexes = new ArrayList<>();
    for (int i = 0; i < numSegments; i++) {
        log.info("Generating rows for segment " + i);
        DataGenerator gen = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED + i, schemaInfo.getDataInterval(), rowsPerSegment);
        IncrementalIndex incIndex = makeIncIndex();
        for (int j = 0; j < rowsPerSegment; j++) {
            InputRow row = gen.nextRow();
            if (j % 10000 == 0) {
                log.info(j + " rows generated.");
            }
            incIndex.add(row);
        }
        incIndexes.add(incIndex);
    }
    File tmpFile = FileUtils.createTempDir();
    log.info("Using temp dir: " + tmpFile.getAbsolutePath());
    tmpFile.deleteOnExit();
    qIndexes = new ArrayList<>();
    for (int i = 0; i < numSegments; i++) {
        File indexFile = INDEX_MERGER_V9.persist(incIndexes.get(i), tmpFile, new IndexSpec(), null);
        QueryableIndex qIndex = INDEX_IO.loadIndex(indexFile);
        qIndexes.add(qIndex);
    }
    factory = new TopNQueryRunnerFactory(new StupidPool<>("TopNBenchmark-compute-bufferPool", new OffheapBufferGenerator("compute", 250000000), 0, Integer.MAX_VALUE), new TopNQueryQueryToolChest(new TopNQueryConfig()), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
}

Example 13 with DataGenerator

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

the class TimeCompareBenchmark method setup.

@Setup
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + System.currentTimeMillis());
    ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde());
    executorService = Execs.multiThreaded(numSegments, "TopNThreadPool");
    setupQueries();
    String schemaName = "basic";
    schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get(schemaName);
    segmentIntervals = new Interval[numSegments];
    long startMillis = schemaInfo.getDataInterval().getStartMillis();
    long endMillis = schemaInfo.getDataInterval().getEndMillis();
    long partialIntervalMillis = (endMillis - startMillis) / numSegments;
    for (int i = 0; i < numSegments; i++) {
        long partialEndMillis = startMillis + partialIntervalMillis;
        segmentIntervals[i] = Intervals.utc(startMillis, partialEndMillis);
        log.info("Segment [%d] with interval [%s]", i, segmentIntervals[i]);
        startMillis = partialEndMillis;
    }
    incIndexes = new ArrayList<>();
    for (int i = 0; i < numSegments; i++) {
        log.info("Generating rows for segment " + i);
        DataGenerator gen = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED + i, segmentIntervals[i], rowsPerSegment);
        IncrementalIndex incIndex = makeIncIndex();
        for (int j = 0; j < rowsPerSegment; j++) {
            InputRow row = gen.nextRow();
            if (j % 10000 == 0) {
                log.info(j + " rows generated.");
            }
            incIndex.add(row);
        }
        incIndexes.add(incIndex);
    }
    tmpDir = FileUtils.createTempDir();
    log.info("Using temp dir: " + tmpDir.getAbsolutePath());
    qIndexes = new ArrayList<>();
    for (int i = 0; i < numSegments; i++) {
        File indexFile = INDEX_MERGER_V9.persist(incIndexes.get(i), tmpDir, new IndexSpec(), null);
        QueryableIndex qIndex = INDEX_IO.loadIndex(indexFile);
        qIndexes.add(qIndex);
    }
    List<QueryRunner<Result<TopNResultValue>>> singleSegmentRunners = new ArrayList<>();
    QueryToolChest toolChest = topNFactory.getToolchest();
    for (int i = 0; i < numSegments; i++) {
        SegmentId segmentId = SegmentId.dummy("qIndex " + i);
        QueryRunner<Result<TopNResultValue>> runner = QueryBenchmarkUtil.makeQueryRunner(topNFactory, segmentId, new QueryableIndexSegment(qIndexes.get(i), segmentId));
        singleSegmentRunners.add(new PerSegmentOptimizingQueryRunner<>(toolChest.preMergeQueryDecoration(runner), new PerSegmentQueryOptimizationContext(new SegmentDescriptor(segmentIntervals[i], "1", 0))));
    }
    topNRunner = toolChest.postMergeQueryDecoration(new FinalizeResultsQueryRunner<>(toolChest.mergeResults(topNFactory.mergeRunners(executorService, singleSegmentRunners)), toolChest));
    List<QueryRunner<Result<TimeseriesResultValue>>> singleSegmentRunnersT = new ArrayList<>();
    QueryToolChest toolChestT = timeseriesFactory.getToolchest();
    for (int i = 0; i < numSegments; i++) {
        SegmentId segmentId = SegmentId.dummy("qIndex " + i);
        QueryRunner<Result<TimeseriesResultValue>> runner = QueryBenchmarkUtil.makeQueryRunner(timeseriesFactory, segmentId, new QueryableIndexSegment(qIndexes.get(i), segmentId));
        singleSegmentRunnersT.add(new PerSegmentOptimizingQueryRunner<>(toolChestT.preMergeQueryDecoration(runner), new PerSegmentQueryOptimizationContext(new SegmentDescriptor(segmentIntervals[i], "1", 0))));
    }
    timeseriesRunner = toolChestT.postMergeQueryDecoration(new FinalizeResultsQueryRunner<>(toolChestT.mergeResults(timeseriesFactory.mergeRunners(executorService, singleSegmentRunnersT)), toolChestT));
}

Example 14 with DataGenerator

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

the class SearchBenchmark method setup.

/**
 * Setup everything common for benchmarking both the incremental-index and the queriable-index.
 */
@Setup
public void setup() {
    log.info("SETUP CALLED AT " + +System.currentTimeMillis());
    ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde());
    setupQueries();
    String[] schemaQuery = schemaAndQuery.split("\\.");
    String schemaName = schemaQuery[0];
    String queryName = schemaQuery[1];
    schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get(schemaName);
    queryBuilder = SCHEMA_QUERY_MAP.get(schemaName).get(queryName);
    queryBuilder.limit(limit);
    query = queryBuilder.build();
    generator = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
    final SearchQueryConfig config = new SearchQueryConfig().withOverrides(query);
    factory = new SearchQueryRunnerFactory(new SearchStrategySelector(Suppliers.ofInstance(config)), new SearchQueryQueryToolChest(config), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
}

Example 15 with DataGenerator

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

the class GeneratorInputSourceTest method testReader.

@Test
public void testReader() throws IOException {
    final long seed = 1024L;
    final long millis = DateTimes.nowUtc().getMillis();
    final int numConsecutiveTimestamps = 1000;
    final double timestampIncrement = 1.0;
    final int numRows = 1000;
    GeneratorInputSource inputSource = new GeneratorInputSource("basic", null, numRows, 2, seed, millis, numConsecutiveTimestamps, timestampIncrement);
    DataGenerator generator = new DataGenerator(GeneratorBasicSchemas.SCHEMA_MAP.get("basic").getColumnSchemas(), seed, millis, numConsecutiveTimestamps, timestampIncrement);
    InputSourceReader reader = inputSource.fixedFormatReader(null, null);
    CloseableIterator<InputRow> iterator = reader.read();
    InputRow first = iterator.next();
    InputRow generatorFirst = generator.nextRow();
    Assert.assertEquals(generatorFirst, first);
    Assert.assertTrue(iterator.hasNext());
    int i;
    for (i = 1; iterator.hasNext(); i++) {
        iterator.next();
    }
    Assert.assertEquals(numRows, i);
}