clintropolis commented on a change in pull request #11597: URL: https://github.com/apache/druid/pull/11597#discussion_r723045248
########## File path: sql/src/test/java/org/apache/druid/sql/calcite/schema/SegmentsTableBenchamrkBase.java ########## @@ -0,0 +1,374 @@ +/* + * 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.sql.calcite.schema; + +import com.fasterxml.jackson.databind.ObjectMapper; +import com.google.common.collect.ImmutableList; +import com.google.common.collect.ImmutableMap; +import org.apache.druid.client.BrokerSegmentWatcherConfig; +import org.apache.druid.common.config.NullHandling; +import org.apache.druid.data.input.impl.DimensionSchema; +import org.apache.druid.data.input.impl.DimensionsSpec; +import org.apache.druid.data.input.impl.StringDimensionSchema; +import org.apache.druid.discovery.DruidLeaderClient; +import org.apache.druid.discovery.DruidNodeDiscoveryProvider; +import org.apache.druid.discovery.NodeRole; +import org.apache.druid.jackson.DefaultObjectMapper; +import org.apache.druid.java.util.common.Intervals; +import org.apache.druid.java.util.common.NonnullPair; +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.guava.Sequences; +import org.apache.druid.java.util.common.io.Closer; +import org.apache.druid.query.QueryRunnerFactoryConglomerate; +import org.apache.druid.query.QuerySegmentWalker; +import org.apache.druid.query.aggregation.AggregatorFactory; +import org.apache.druid.query.aggregation.CountAggregatorFactory; +import org.apache.druid.query.metadata.metadata.SegmentAnalysis; +import org.apache.druid.segment.incremental.IncrementalIndexSchema; +import org.apache.druid.segment.loading.SegmentLoader; +import org.apache.druid.server.QueryLifecycleFactory; +import org.apache.druid.server.QueryStackTests; +import org.apache.druid.server.SegmentManager; +import org.apache.druid.server.security.AuthTestUtils; +import org.apache.druid.server.security.AuthenticationResult; +import org.apache.druid.server.security.AuthorizerMapper; +import org.apache.druid.sql.calcite.planner.Calcites; +import org.apache.druid.sql.calcite.planner.PlannerConfig; +import org.apache.druid.sql.calcite.planner.PlannerFactory; +import org.apache.druid.sql.calcite.planner.SegmentsTableConfig; +import org.apache.druid.sql.calcite.util.CalciteTests; +import org.apache.druid.sql.calcite.util.CalciteTests.FakeDruidNodeDiscoveryProvider; +import org.apache.druid.sql.calcite.util.CalciteTests.FakeHttpClient; +import org.apache.druid.sql.calcite.util.CalciteTests.FakeServerInventoryView; +import org.apache.druid.sql.calcite.util.SpecificSegmentsQuerySegmentWalker; +import org.apache.druid.sql.calcite.util.TestServerInventoryView; +import org.apache.druid.timeline.DataSegment; +import org.apache.druid.timeline.SegmentId; +import org.apache.druid.timeline.SegmentWithOvershadowedStatus; +import org.apache.druid.timeline.partition.NumberedShardSpec; +import org.easymock.EasyMock; +import org.joda.time.Interval; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Iterator; +import java.util.List; +import java.util.Set; +import java.util.SortedSet; +import java.util.TreeMap; +import java.util.TreeSet; +import java.util.stream.Collectors; + +public abstract class SegmentsTableBenchamrkBase Review comment: typo: `SegmentsTableBenchamrkBase` -> `SegmentsTableBenchmarkBase` Side thought/nitpick, `Benchmark` doesn't seem like quite the right name since it is just setting up a set of queries to do stuff with, and happens to be used by some actual benchmarks alongside tests. But, i'm not really sure what would be a better name.. something query suite? naming is the worst, and since this is just a test class it doesn't really matter... ########## File path: docs/configuration/index.md ########## @@ -1764,6 +1764,8 @@ The Druid SQL server is configured through the following properties on the Broke |`druid.sql.planner.metadataSegmentCacheEnable`|Whether to keep a cache of published segments in broker. If true, broker polls coordinator in background to get segments from metadata store and maintains a local cache. If false, coordinator's REST API will be invoked when broker needs published segments info.|false| |`druid.sql.planner.metadataSegmentPollPeriod`|How often to poll coordinator for published segments list if `druid.sql.planner.metadataSegmentCacheEnable` is set to true. Poll period is in milliseconds. |60000| |`druid.sql.planner.authorizeSystemTablesDirectly`|If true, Druid authorizes queries against any of the system schema tables (`sys` in SQL) as `SYSTEM_TABLE` resources which require `READ` access, in addition to permissions based content filtering.|false| +|`druid.sql.sys.segments.forceHashBasedMerge`|When `druid.sql.planner.metadataSegmentCacheEnable` is set to true, the broker uses a sort-based algorithm by default for merging the sets of published segments and available segments to process the `sys.segments` table. You can force using a hash-based merge algorithm by setting this config even when the cache is enabled. The sort-based algorithm is supposed to be faster than the hash-based algorithm in most cases.|false| Review comment: ```suggestion |`druid.sql.sys.segments.forceHashBasedMerge`|When `druid.sql.planner.metadataSegmentCacheEnable` is set to true, the broker uses a sort-based algorithm by default for merging the sets of published and available segments to process the `sys.segments` table. Use of the hash-based merge algorithm can be forced by setting this to true, even when the cache is enabled. The sort-based algorithm should be faster than the hash-based algorithm in most cases.|false| ``` ########## File path: sql/src/main/java/org/apache/druid/sql/calcite/schema/ObjectStringCache.java ########## @@ -0,0 +1,83 @@ +/* + * 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.sql.calcite.schema; + +import org.apache.druid.common.guava.SettableSupplier; + +import javax.annotation.Nullable; +import java.util.HashMap; +import java.util.Map; +import java.util.function.Function; + +/** + * A simple cache to hold string representation of the given keys. + * This cache can be used to avoid repetitive calls of expensive {@link Object#toString()} + * or JSON serializations. + * + * This cache uses a simple caching policy that keeps only the first N entries. + * The cache size is limited by the {@link #cacheSize} constructor parameter. + * + * @param <K> cache key type + * + * @see SegmentsTableRow#toObjectArray + */ +class ObjectStringCache<K> Review comment: maybe this class deserves its own tests? Also I wonder if using caffeine for a cache so to evict items not recently used might be better behavior than caching the first 'n'? ########## File path: sql/src/test/java/org/apache/druid/sql/calcite/schema/SegmentsTableBenchmarkQueryTest.java ########## @@ -0,0 +1,129 @@ +/* + * 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.sql.calcite.schema; + +import com.google.common.collect.ImmutableList; +import com.google.common.collect.ImmutableMap; +import org.apache.calcite.sql.parser.SqlParseException; +import org.apache.calcite.tools.RelConversionException; +import org.apache.calcite.tools.ValidationException; +import org.apache.druid.common.guava.SettableSupplier; +import org.apache.druid.sql.calcite.planner.DruidPlanner; +import org.apache.druid.sql.calcite.planner.PlannerConfig; +import org.apache.druid.sql.calcite.planner.PlannerResult; +import org.apache.druid.sql.calcite.planner.SegmentsTableConfig; +import org.junit.AfterClass; +import org.junit.Assert; +import org.junit.BeforeClass; +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +import java.io.IOException; +import java.util.List; + +@RunWith(Parameterized.class) +public class SegmentsTableBenchmarkQueryTest extends SegmentsTableBenchamrkBase Review comment: similar nit about naming since this isn't testing the benchmark -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
