Examples with BenchmarkDataGenerator io.druid.benchmark.datagen.BenchmarkDataGenerator used on opensource projects

Example 11 with BenchmarkDataGenerator

use of io.druid.benchmark.datagen.BenchmarkDataGenerator in project druid by druid-io.

the class FilterPartitionBenchmark method setup.

@Setup
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + System.currentTimeMillis());
    if (ComplexMetrics.getSerdeForType("hyperUnique") == null) {
        ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde(HyperLogLogHash.getDefault()));
    }
    schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schema);
    BenchmarkDataGenerator gen = new BenchmarkDataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
    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);
    }
    tmpDir = Files.createTempDir();
    log.info("Using temp dir: " + tmpDir.getAbsolutePath());
    indexFile = INDEX_MERGER_V9.persist(incIndex, tmpDir, new IndexSpec());
    qIndex = INDEX_IO.loadIndex(indexFile);
    Interval interval = schemaInfo.getDataInterval();
    timeFilterNone = new BoundFilter(new BoundDimFilter(Column.TIME_COLUMN_NAME, String.valueOf(Long.MAX_VALUE), String.valueOf(Long.MAX_VALUE), true, true, null, null, StringComparators.ALPHANUMERIC));
    long halfEnd = (interval.getEndMillis() + interval.getStartMillis()) / 2;
    timeFilterHalf = new BoundFilter(new BoundDimFilter(Column.TIME_COLUMN_NAME, String.valueOf(interval.getStartMillis()), String.valueOf(halfEnd), true, true, null, null, StringComparators.ALPHANUMERIC));
    timeFilterAll = new BoundFilter(new BoundDimFilter(Column.TIME_COLUMN_NAME, String.valueOf(interval.getStartMillis()), String.valueOf(interval.getEndMillis()), true, true, null, null, StringComparators.ALPHANUMERIC));
}

Example 12 with BenchmarkDataGenerator

use of io.druid.benchmark.datagen.BenchmarkDataGenerator in project druid by druid-io.

the class FilteredAggregatorBenchmark method setup.

@Setup
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + System.currentTimeMillis());
    if (ComplexMetrics.getSerdeForType("hyperUnique") == null) {
        ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde(HyperLogLogHash.getDefault()));
    }
    schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schema);
    BenchmarkDataGenerator gen = new BenchmarkDataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
    incIndex = makeIncIndex(schemaInfo.getAggsArray());
    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)));
    filteredMetrics = new AggregatorFactory[1];
    filteredMetrics[0] = new FilteredAggregatorFactory(new CountAggregatorFactory("rows"), filter);
    incIndexFilteredAgg = makeIncIndex(filteredMetrics);
    inputRows = new ArrayList<>();
    for (int j = 0; j < rowsPerSegment; j++) {
        InputRow row = gen.nextRow();
        if (j % 10000 == 0) {
            log.info(j + " rows generated.");
        }
        incIndex.add(row);
        inputRows.add(row);
    }
    tmpDir = Files.createTempDir();
    log.info("Using temp dir: " + tmpDir.getAbsolutePath());
    indexFile = INDEX_MERGER_V9.persist(incIndex, tmpDir, new IndexSpec());
    qIndex = INDEX_IO.loadIndex(indexFile);
    factory = new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(QueryBenchmarkUtil.NoopIntervalChunkingQueryRunnerDecorator()), new TimeseriesQueryEngine(), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
    BenchmarkSchemaInfo basicSchema = BenchmarkSchemas.SCHEMA_MAP.get("basic");
    QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Arrays.asList(basicSchema.getDataInterval()));
    List<AggregatorFactory> queryAggs = new ArrayList<>();
    queryAggs.add(filteredMetrics[0]);
    query = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(false).build();
}

Example 13 with BenchmarkDataGenerator

use of io.druid.benchmark.datagen.BenchmarkDataGenerator in project druid by druid-io.

the class IndexIngestionBenchmark method setup.

@Setup
public void setup() throws IOException {
    ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde(HyperLogLogHash.getDefault()));
    rows = new ArrayList<InputRow>();
    schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schema);
    BenchmarkDataGenerator gen = new BenchmarkDataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
    for (int i = 0; i < rowsPerSegment; i++) {
        InputRow row = gen.nextRow();
        if (i % 10000 == 0) {
            log.info(i + " rows generated.");
        }
        rows.add(row);
    }
}

Example 14 with BenchmarkDataGenerator

use of io.druid.benchmark.datagen.BenchmarkDataGenerator in project druid by druid-io.

the class IndexMergeBenchmark method setup.

@Setup
public void setup() throws IOException {
    log.info("SETUP CALLED AT " + +System.currentTimeMillis());
    if (ComplexMetrics.getSerdeForType("hyperUnique") == null) {
        ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde(HyperLogLogHash.getDefault()));
    }
    indexesToMerge = new ArrayList<>();
    schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schema);
    for (int i = 0; i < numSegments; i++) {
        BenchmarkDataGenerator gen = new BenchmarkDataGenerator(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);
        }
        tmpDir = Files.createTempDir();
        log.info("Using temp dir: " + tmpDir.getAbsolutePath());
        File indexFile = INDEX_MERGER_V9.persist(incIndex, tmpDir, new IndexSpec());
        QueryableIndex qIndex = INDEX_IO.loadIndex(indexFile);
        indexesToMerge.add(qIndex);
    }
}

Example 15 with BenchmarkDataGenerator

use of io.druid.benchmark.datagen.BenchmarkDataGenerator 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()));
}