lamber-ken commented on a change in pull request #1469: [HUDI-686] Implement BloomIndexV2 that does not depend on memory caching URL: https://github.com/apache/incubator-hudi/pull/1469#discussion_r407136936
########## File path: hudi-client/src/main/java/org/apache/hudi/index/bloom/HoodieBloomIndexV2.java ########## @@ -0,0 +1,324 @@ +/* + * 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.hudi.index.bloom; + +import org.apache.hudi.client.WriteStatus; +import org.apache.hudi.client.utils.LazyIterableIterator; +import org.apache.hudi.common.bloom.BloomFilter; +import org.apache.hudi.common.model.HoodieBaseFile; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieRecordLocation; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.common.table.timeline.HoodieInstant; +import org.apache.hudi.common.util.DefaultSizeEstimator; +import org.apache.hudi.common.util.DeltaTimer; +import org.apache.hudi.common.util.HoodieTimer; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.collection.ExternalSpillableMap; +import org.apache.hudi.common.util.collection.Pair; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieIOException; +import org.apache.hudi.index.HoodieIndex; +import org.apache.hudi.io.HoodieBloomRangeInfoHandle; +import org.apache.hudi.io.HoodieKeyLookupHandle; +import org.apache.hudi.table.HoodieTable; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaPairRDD; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.api.java.JavaSparkContext; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.Iterator; +import java.util.List; +import java.util.Objects; +import java.util.Set; +import java.util.function.Function; +import java.util.stream.Collectors; + +/** + * Simplified re-implementation of {@link HoodieBloomIndex} that does not rely on caching, or + * incurs the overhead of auto-tuning parallelism. + */ +public class HoodieBloomIndexV2<T extends HoodieRecordPayload> extends HoodieIndex<T> { Review comment: Ok, let's spread the good news to community firstly and get feedback. After a period of time, if there is no bug, will take https://issues.apache.org/jira/browse/HUDI-787 ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services