YuweiXiao commented on code in PR #4958: URL: https://github.com/apache/hudi/pull/4958#discussion_r917394901
########## hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/client/clustering/plan/strategy/SparkConsistentBucketClusteringPlanStrategy.java: ########## @@ -0,0 +1,332 @@ +/* + * 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.client.clustering.plan.strategy; + +import org.apache.hudi.avro.model.HoodieClusteringGroup; +import org.apache.hudi.client.WriteStatus; +import org.apache.hudi.common.engine.HoodieEngineContext; +import org.apache.hudi.common.fs.FSUtils; +import org.apache.hudi.common.model.ConsistentHashingNode; +import org.apache.hudi.common.model.FileSlice; +import org.apache.hudi.common.model.HoodieConsistentHashingMetadata; +import org.apache.hudi.common.model.HoodieFileFormat; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.common.model.HoodieRecordPayload; +import org.apache.hudi.common.table.timeline.HoodieTimeline; +import org.apache.hudi.common.table.view.SyncableFileSystemView; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.StringUtils; +import org.apache.hudi.common.util.ValidationUtils; +import org.apache.hudi.common.util.collection.Triple; +import org.apache.hudi.config.HoodieClusteringConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieClusteringException; +import org.apache.hudi.index.bucket.ConsistentBucketIdentifier; +import org.apache.hudi.index.bucket.HoodieSparkConsistentBucketIndex; +import org.apache.hudi.table.HoodieTable; +import org.apache.hudi.table.action.cluster.strategy.PartitionAwareClusteringPlanStrategy; + +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaRDD; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.Collections; +import java.util.Comparator; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; +import java.util.stream.IntStream; +import java.util.stream.Stream; + +/** + * Clustering plan strategy specifically for consistent bucket index + */ +public class SparkConsistentBucketClusteringPlanStrategy<T extends HoodieRecordPayload<T>> + extends PartitionAwareClusteringPlanStrategy<T, JavaRDD<HoodieRecord<T>>, JavaRDD<HoodieKey>, JavaRDD<WriteStatus>> { + + private static final Logger LOG = LogManager.getLogger(SparkConsistentBucketClusteringPlanStrategy.class); + + public static final String METADATA_PARTITION_KEY = "clustering.group.partition"; + public static final String METADATA_CHILD_NODE_KEY = "clustering.group.child.node"; + public static final String METADATA_SEQUENCE_NUMBER_KEY = "clustering.group.sequence.no"; + + public SparkConsistentBucketClusteringPlanStrategy(HoodieTable table, HoodieEngineContext engineContext, HoodieWriteConfig writeConfig) { + super(table, engineContext, writeConfig); + validate(); + } + + /** + * TODO maybe add force config to schedule the clustering. It could allow clustering on partitions that are not doing write operation. + * Block clustering if there is any ongoing concurrent writers + * + * @return true if the schedule can proceed + */ + @Override + public boolean checkPrecondition() { + HoodieTimeline timeline = getHoodieTable().getActiveTimeline().getDeltaCommitTimeline().filterInflightsAndRequested(); Review Comment: Consistent hashing bucket index now only works for MOR table, so delta commit timeline is enough here. -- 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]
