use of org.apache.druid.query.topn.TopNQueryRunnerFactory in project druid by druid-io.
the class QueryStackTests method createQueryRunnerFactoryConglomerate.
public static QueryRunnerFactoryConglomerate createQueryRunnerFactoryConglomerate(final Closer closer, final DruidProcessingConfig processingConfig, final Supplier<Integer> minTopNThresholdSupplier) {
final CloseableStupidPool<ByteBuffer> stupidPool = new CloseableStupidPool<>("TopNQueryRunnerFactory-bufferPool", () -> ByteBuffer.allocate(COMPUTE_BUFFER_SIZE));
closer.register(stupidPool);
final Pair<GroupByQueryRunnerFactory, Closer> factoryCloserPair = GroupByQueryRunnerTest.makeQueryRunnerFactory(GroupByQueryRunnerTest.DEFAULT_MAPPER, new GroupByQueryConfig() {
@Override
public String getDefaultStrategy() {
return GroupByStrategySelector.STRATEGY_V2;
}
}, processingConfig);
final GroupByQueryRunnerFactory groupByQueryRunnerFactory = factoryCloserPair.lhs;
closer.register(factoryCloserPair.rhs);
final QueryRunnerFactoryConglomerate conglomerate = new DefaultQueryRunnerFactoryConglomerate(ImmutableMap.<Class<? extends Query>, QueryRunnerFactory>builder().put(SegmentMetadataQuery.class, new SegmentMetadataQueryRunnerFactory(new SegmentMetadataQueryQueryToolChest(new SegmentMetadataQueryConfig("P1W")), QueryRunnerTestHelper.NOOP_QUERYWATCHER)).put(ScanQuery.class, new ScanQueryRunnerFactory(new ScanQueryQueryToolChest(new ScanQueryConfig(), new DefaultGenericQueryMetricsFactory()), new ScanQueryEngine(), new ScanQueryConfig())).put(TimeseriesQuery.class, new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(), new TimeseriesQueryEngine(), QueryRunnerTestHelper.NOOP_QUERYWATCHER)).put(TopNQuery.class, new TopNQueryRunnerFactory(stupidPool, new TopNQueryQueryToolChest(new TopNQueryConfig() {
@Override
public int getMinTopNThreshold() {
return minTopNThresholdSupplier.get();
}
}), QueryRunnerTestHelper.NOOP_QUERYWATCHER)).put(GroupByQuery.class, groupByQueryRunnerFactory).build());
return conglomerate;
}
use of org.apache.druid.query.topn.TopNQueryRunnerFactory in project druid by druid-io.
the class CachingClusteredClientBenchmark method setup.
@Setup(Level.Trial)
public void setup() {
final String schemaName = "basic";
parallelCombine = parallelism > 0;
GeneratorSchemaInfo schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get(schemaName);
Map<DataSegment, QueryableIndex> queryableIndexes = Maps.newHashMapWithExpectedSize(numServers);
for (int i = 0; i < numServers; i++) {
final DataSegment dataSegment = DataSegment.builder().dataSource(DATA_SOURCE).interval(schemaInfo.getDataInterval()).version("1").shardSpec(new LinearShardSpec(i)).size(0).build();
final SegmentGenerator segmentGenerator = closer.register(new SegmentGenerator());
LOG.info("Starting benchmark setup using cacheDir[%s], rows[%,d].", segmentGenerator.getCacheDir(), rowsPerSegment);
final QueryableIndex index = segmentGenerator.generate(dataSegment, schemaInfo, Granularities.NONE, rowsPerSegment);
queryableIndexes.put(dataSegment, index);
}
final DruidProcessingConfig processingConfig = new DruidProcessingConfig() {
@Override
public String getFormatString() {
return null;
}
@Override
public int intermediateComputeSizeBytes() {
return PROCESSING_BUFFER_SIZE;
}
@Override
public int getNumMergeBuffers() {
return 1;
}
@Override
public int getNumThreads() {
return numProcessingThreads;
}
@Override
public boolean useParallelMergePool() {
return true;
}
};
conglomerate = new DefaultQueryRunnerFactoryConglomerate(ImmutableMap.<Class<? extends Query>, QueryRunnerFactory>builder().put(TimeseriesQuery.class, new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(), new TimeseriesQueryEngine(), QueryRunnerTestHelper.NOOP_QUERYWATCHER)).put(TopNQuery.class, new TopNQueryRunnerFactory(new StupidPool<>("TopNQueryRunnerFactory-bufferPool", () -> ByteBuffer.allocate(PROCESSING_BUFFER_SIZE)), new TopNQueryQueryToolChest(new TopNQueryConfig()), QueryRunnerTestHelper.NOOP_QUERYWATCHER)).put(GroupByQuery.class, makeGroupByQueryRunnerFactory(GroupByQueryRunnerTest.DEFAULT_MAPPER, new GroupByQueryConfig() {
@Override
public String getDefaultStrategy() {
return GroupByStrategySelector.STRATEGY_V2;
}
}, processingConfig)).build());
toolChestWarehouse = new QueryToolChestWarehouse() {
@Override
public <T, QueryType extends Query<T>> QueryToolChest<T, QueryType> getToolChest(final QueryType query) {
return conglomerate.findFactory(query).getToolchest();
}
};
SimpleServerView serverView = new SimpleServerView();
int serverSuffx = 1;
for (Entry<DataSegment, QueryableIndex> entry : queryableIndexes.entrySet()) {
serverView.addServer(createServer(serverSuffx++), entry.getKey(), entry.getValue());
}
processingPool = Execs.multiThreaded(processingConfig.getNumThreads(), "caching-clustered-client-benchmark");
forkJoinPool = new ForkJoinPool((int) Math.ceil(Runtime.getRuntime().availableProcessors() * 0.75), ForkJoinPool.defaultForkJoinWorkerThreadFactory, null, true);
cachingClusteredClient = new CachingClusteredClient(toolChestWarehouse, serverView, MapCache.create(0), JSON_MAPPER, new ForegroundCachePopulator(JSON_MAPPER, new CachePopulatorStats(), 0), new CacheConfig(), new DruidHttpClientConfig(), processingConfig, forkJoinPool, QueryStackTests.DEFAULT_NOOP_SCHEDULER, new MapJoinableFactory(ImmutableSet.of(), ImmutableMap.of()), new NoopServiceEmitter());
}
use of org.apache.druid.query.topn.TopNQueryRunnerFactory in project druid by druid-io.
the class TimeCompareBenchmark method setupQueries.
private void setupQueries() {
// queries for the basic schema
GeneratorSchemaInfo basicSchema = GeneratorBasicSchemas.SCHEMA_MAP.get("basic");
QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(basicSchema.getDataInterval()));
long startMillis = basicSchema.getDataInterval().getStartMillis();
long endMillis = basicSchema.getDataInterval().getEndMillis();
long half = (endMillis - startMillis) / 2;
Interval recent = Intervals.utc(half, endMillis);
Interval previous = Intervals.utc(startMillis, half);
log.info("Recent interval: " + recent);
log.info("Previous interval: " + previous);
{
// basic.topNTimeCompare
List<AggregatorFactory> queryAggs = new ArrayList<>();
queryAggs.add(new FilteredAggregatorFactory(// jsAgg1,
new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential"), new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Collections.singletonList(recent), null)));
queryAggs.add(new FilteredAggregatorFactory(new LongSumAggregatorFactory("_cmp_sumLongSequential", "sumLongSequential"), new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Collections.singletonList(previous), null)));
TopNQueryBuilder queryBuilderA = new TopNQueryBuilder().dataSource("blah").granularity(Granularities.ALL).dimension("dimUniform").metric("sumLongSequential").intervals(intervalSpec).aggregators(queryAggs).threshold(threshold);
topNQuery = queryBuilderA.build();
topNFactory = new TopNQueryRunnerFactory(new StupidPool<>("TopNBenchmark-compute-bufferPool", new OffheapBufferGenerator("compute", 250000000), 0, Integer.MAX_VALUE), new TopNQueryQueryToolChest(new TopNQueryConfig()), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
}
{
// basic.timeseriesTimeCompare
List<AggregatorFactory> queryAggs = new ArrayList<>();
queryAggs.add(new FilteredAggregatorFactory(new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential"), new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Collections.singletonList(recent), null)));
queryAggs.add(new FilteredAggregatorFactory(new LongSumAggregatorFactory("_cmp_sumLongSequential", "sumLongSequential"), new IntervalDimFilter(ColumnHolder.TIME_COLUMN_NAME, Collections.singletonList(previous), null)));
Druids.TimeseriesQueryBuilder timeseriesQueryBuilder = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(false);
timeseriesQuery = timeseriesQueryBuilder.build();
timeseriesFactory = new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(), new TimeseriesQueryEngine(), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
}
}
use of org.apache.druid.query.topn.TopNQueryRunnerFactory in project druid by druid-io.
the class TopNBenchmark 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.threshold(threshold);
query = queryBuilder.build();
generator = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
factory = new TopNQueryRunnerFactory(new StupidPool<>("TopNBenchmark-compute-bufferPool", new OffheapBufferGenerator("compute", 250000000), 0, Integer.MAX_VALUE), new TopNQueryQueryToolChest(new TopNQueryConfig()), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
}
use of org.apache.druid.query.topn.TopNQueryRunnerFactory in project druid by druid-io.
the class MapVirtualColumnTopNTest method setup.
@Before
public void setup() throws IOException {
final IncrementalIndex incrementalIndex = MapVirtualColumnTestBase.generateIndex();
final TopNQueryRunnerFactory factory = new TopNQueryRunnerFactory(new StupidPool<>("map-virtual-column-test", () -> ByteBuffer.allocate(1024)), new TopNQueryQueryToolChest(new TopNQueryConfig()), QueryRunnerTestHelper.NOOP_QUERYWATCHER);
runner = QueryRunnerTestHelper.makeQueryRunner(factory, SegmentId.dummy("index1"), new IncrementalIndexSegment(incrementalIndex, SegmentId.dummy("index1")), "incremental");
}
Aggregations