[GitHub] [incubator-druid] leventov commented on a change in pull request #8089: add CachingClusteredClient benchmark, refactor some stuff

[GitBox <gi...@apache.org>]

leventov commented on a change in pull request #8089: add CachingClusteredClient benchmark, refactor some stuff
URL: https://github.com/apache/incubator-druid/pull/8089#discussion_r304444669
 
 

 ##########
 File path: benchmarks/src/main/java/org/apache/druid/benchmark/query/CachingClusteredClientBenchmark.java
 ##########
 @@ -0,0 +1,569 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.druid.benchmark.query;
+
+import com.fasterxml.jackson.databind.InjectableValues.Std;
+import com.fasterxml.jackson.databind.ObjectMapper;
+import com.google.common.base.Preconditions;
+import com.google.common.base.Supplier;
+import com.google.common.base.Suppliers;
+import com.google.common.collect.ImmutableMap;
+import com.google.common.collect.Iterables;
+import com.google.common.collect.Ordering;
+import org.apache.druid.benchmark.datagen.BenchmarkSchemaInfo;
+import org.apache.druid.benchmark.datagen.BenchmarkSchemas;
+import org.apache.druid.benchmark.datagen.SegmentGenerator;
+import org.apache.druid.client.CachingClusteredClient;
+import org.apache.druid.client.DruidServer;
+import org.apache.druid.client.ImmutableDruidServer;
+import org.apache.druid.client.TimelineServerView;
+import org.apache.druid.client.cache.CacheConfig;
+import org.apache.druid.client.cache.CachePopulatorStats;
+import org.apache.druid.client.cache.ForegroundCachePopulator;
+import org.apache.druid.client.cache.MapCache;
+import org.apache.druid.client.selector.HighestPriorityTierSelectorStrategy;
+import org.apache.druid.client.selector.QueryableDruidServer;
+import org.apache.druid.client.selector.RandomServerSelectorStrategy;
+import org.apache.druid.client.selector.ServerSelector;
+import org.apache.druid.client.selector.TierSelectorStrategy;
+import org.apache.druid.collections.BlockingPool;
+import org.apache.druid.collections.DefaultBlockingPool;
+import org.apache.druid.collections.NonBlockingPool;
+import org.apache.druid.collections.StupidPool;
+import org.apache.druid.data.input.Row;
+import org.apache.druid.guice.http.DruidHttpClientConfig;
+import org.apache.druid.jackson.DefaultObjectMapper;
+import org.apache.druid.java.util.common.concurrent.Execs;
+import org.apache.druid.java.util.common.granularity.Granularities;
+import org.apache.druid.java.util.common.granularity.Granularity;
+import org.apache.druid.java.util.common.guava.Sequence;
+import org.apache.druid.java.util.common.io.Closer;
+import org.apache.druid.java.util.common.logger.Logger;
+import org.apache.druid.math.expr.ExprMacroTable;
+import org.apache.druid.query.BySegmentQueryRunner;
+import org.apache.druid.query.DataSource;
+import org.apache.druid.query.DefaultQueryRunnerFactoryConglomerate;
+import org.apache.druid.query.DruidProcessingConfig;
+import org.apache.druid.query.Druids;
+import org.apache.druid.query.FinalizeResultsQueryRunner;
+import org.apache.druid.query.FluentQueryRunnerBuilder;
+import org.apache.druid.query.Query;
+import org.apache.druid.query.QueryPlus;
+import org.apache.druid.query.QueryRunner;
+import org.apache.druid.query.QueryRunnerFactory;
+import org.apache.druid.query.QueryRunnerFactoryConglomerate;
+import org.apache.druid.query.QueryRunnerTestHelper;
+import org.apache.druid.query.QueryToolChest;
+import org.apache.druid.query.QueryToolChestWarehouse;
+import org.apache.druid.query.Result;
+import org.apache.druid.query.aggregation.LongSumAggregatorFactory;
+import org.apache.druid.query.dimension.DefaultDimensionSpec;
+import org.apache.druid.query.expression.TestExprMacroTable;
+import org.apache.druid.query.groupby.GroupByQuery;
+import org.apache.druid.query.groupby.GroupByQueryConfig;
+import org.apache.druid.query.groupby.GroupByQueryEngine;
+import org.apache.druid.query.groupby.GroupByQueryQueryToolChest;
+import org.apache.druid.query.groupby.GroupByQueryRunnerFactory;
+import org.apache.druid.query.groupby.GroupByQueryRunnerTest;
+import org.apache.druid.query.groupby.strategy.GroupByStrategySelector;
+import org.apache.druid.query.groupby.strategy.GroupByStrategyV1;
+import org.apache.druid.query.groupby.strategy.GroupByStrategyV2;
+import org.apache.druid.query.spec.MultipleIntervalSegmentSpec;
+import org.apache.druid.query.spec.QuerySegmentSpec;
+import org.apache.druid.query.timeseries.TimeseriesQuery;
+import org.apache.druid.query.timeseries.TimeseriesQueryEngine;
+import org.apache.druid.query.timeseries.TimeseriesQueryQueryToolChest;
+import org.apache.druid.query.timeseries.TimeseriesQueryRunnerFactory;
+import org.apache.druid.query.timeseries.TimeseriesResultValue;
+import org.apache.druid.query.topn.TopNQuery;
+import org.apache.druid.query.topn.TopNQueryBuilder;
+import org.apache.druid.query.topn.TopNQueryConfig;
+import org.apache.druid.query.topn.TopNQueryQueryToolChest;
+import org.apache.druid.query.topn.TopNQueryRunnerFactory;
+import org.apache.druid.query.topn.TopNResultValue;
+import org.apache.druid.segment.QueryableIndex;
+import org.apache.druid.segment.QueryableIndexSegment;
+import org.apache.druid.server.coordination.ServerType;
+import org.apache.druid.timeline.DataSegment;
+import org.apache.druid.timeline.SegmentId;
+import org.apache.druid.timeline.TimelineLookup;
+import org.apache.druid.timeline.VersionedIntervalTimeline;
+import org.apache.druid.timeline.partition.LinearShardSpec;
+import org.openjdk.jmh.annotations.Benchmark;
+import org.openjdk.jmh.annotations.BenchmarkMode;
+import org.openjdk.jmh.annotations.Fork;
+import org.openjdk.jmh.annotations.Level;
+import org.openjdk.jmh.annotations.Measurement;
+import org.openjdk.jmh.annotations.Mode;
+import org.openjdk.jmh.annotations.OutputTimeUnit;
+import org.openjdk.jmh.annotations.Param;
+import org.openjdk.jmh.annotations.Scope;
+import org.openjdk.jmh.annotations.Setup;
+import org.openjdk.jmh.annotations.State;
+import org.openjdk.jmh.annotations.TearDown;
+import org.openjdk.jmh.annotations.Warmup;
+import org.openjdk.jmh.infra.Blackhole;
+
+import javax.annotation.Nullable;
+import java.io.IOException;
+import java.nio.ByteBuffer;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Map.Entry;
+import java.util.concurrent.Executor;
+import java.util.concurrent.ExecutorService;
+import java.util.concurrent.TimeUnit;
+
+@State(Scope.Benchmark)
+@Fork(value = 1, jvmArgsAppend = "-XX:+UseG1GC")
+@Warmup(iterations = 15)
+@Measurement(iterations = 30)
+public class CachingClusteredClientBenchmark
+{
+  @Param({"8"})
+  private int numServers;
+
+  @Param({"4", "2", "1"})
+  private int numProcessingThreads;
+
+  @Param({"75000"})
+  private int rowsPerSegment;
+
+  @Param({"all"})
+  private String queryGranularity;
+
+  private static final Logger log = new Logger(CachingClusteredClientBenchmark.class);
+  private static final String DATA_SOURCE = "ds";
+  public static final ObjectMapper JSON_MAPPER;
+
+  private QueryToolChestWarehouse toolChestWarehouse;
+  private QueryRunnerFactoryConglomerate conglomerate;
+  private CachingClusteredClient cachingClusteredClient;
+  private ExecutorService processingPool;
+
+  private Query query;
+
+  private final Closer closer = Closer.create();
+
+  private final BenchmarkSchemaInfo basicSchema = BenchmarkSchemas.SCHEMA_MAP.get("basic");
+  private final QuerySegmentSpec basicSchemaIntervalSpec = new MultipleIntervalSegmentSpec(
+      Collections.singletonList(basicSchema.getDataInterval())
+  );
+
+  static {
+    JSON_MAPPER = new DefaultObjectMapper();
+    JSON_MAPPER.setInjectableValues(
+        new Std()
+            .addValue(ExprMacroTable.class.getName(), TestExprMacroTable.INSTANCE)
+            .addValue(ObjectMapper.class.getName(), JSON_MAPPER)
+            .addValue(DataSegment.PruneLoadSpecHolder.class, DataSegment.PruneLoadSpecHolder.DEFAULT)
+    );
+  }
+
+  @Setup(Level.Trial)
+  public void setup()
+  {
+    final String schemaName = "basic";
+
+    BenchmarkSchemaInfo schemaInfo = BenchmarkSchemas.SCHEMA_MAP.get(schemaName);
+
+    Map<DataSegment, QueryableIndex> queryableIndexes = new HashMap<>(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))
+                                                 .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 10 * 1024 * 1024;
+      }
+
+      @Override
+      public int getNumMergeBuffers()
+      {
+        // Need 3 buffers for CalciteQueryTest.testDoubleNestedGroupby.
+        // Two buffers for the broker and one for the queryable
+        return 3;
+      }
+
+      @Override
+      public int getNumThreads()
+      {
+        return numProcessingThreads;
+      }
+    };
+
+    conglomerate = new DefaultQueryRunnerFactoryConglomerate(
+        ImmutableMap.<Class<? extends Query>, QueryRunnerFactory>builder()
+            .put(
+                TimeseriesQuery.class,
+                new TimeseriesQueryRunnerFactory(
+                    new TimeseriesQueryQueryToolChest(
+                        QueryRunnerTestHelper.noopIntervalChunkingQueryRunnerDecorator()
+                    ),
+                    new TimeseriesQueryEngine(),
+                    QueryRunnerTestHelper.NOOP_QUERYWATCHER
+                )
+            )
+            .put(
+                TopNQuery.class,
+                new TopNQueryRunnerFactory(
+                    new StupidPool<>(
+                        "TopNQueryRunnerFactory-bufferPool",
+                        () -> ByteBuffer.allocate(10 * 1024 * 1024)
 
 Review comment:
   Please extract this `10 * 1024 * 1024` together with the one above in the code if they have to be equal or as different constants if they don't have to be equal and comment about that.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@druid.apache.org
For additional commands, e-mail: commits-help@druid.apache.org