YuweiXiao commented on a change in pull request #4480: URL: https://github.com/apache/hudi/pull/4480#discussion_r816413282
########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/index/bucket/HoodieSparkConsistentBucketIndex.java ########## @@ -0,0 +1,218 @@ +/* + * 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.bucket; + +import org.apache.hudi.client.WriteStatus; +import org.apache.hudi.common.data.HoodieData; +import org.apache.hudi.common.engine.HoodieEngineContext; +import org.apache.hudi.common.fs.FSUtils; +import org.apache.hudi.common.fs.HoodieWrapperFileSystem; +import org.apache.hudi.common.model.ConsistentHashingNode; +import org.apache.hudi.common.model.HoodieConsistentHashingMetadata; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecordLocation; +import org.apache.hudi.common.table.timeline.HoodieTimeline; +import org.apache.hudi.common.util.FileIOUtils; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieIOException; +import org.apache.hudi.exception.HoodieIndexException; +import org.apache.hudi.table.HoodieTable; + +import org.apache.hadoop.fs.FSDataOutputStream; +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.Path; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; + +import java.io.IOException; +import java.util.Arrays; +import java.util.Comparator; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.function.Predicate; + +/** + * Consistent hashing bucket index implementation, with auto-adjust bucket number. + * NOTE: bucket resizing is triggered by clustering. + */ +public class HoodieSparkConsistentBucketIndex extends HoodieBucketIndex { + + private static final Logger LOG = LogManager.getLogger(HoodieSparkConsistentBucketIndex.class); + + private Map<String, ConsistentBucketIdentifier> partitionToIdentifier; + + public HoodieSparkConsistentBucketIndex(HoodieWriteConfig config) { + super(config); + } + + @Override + public HoodieData<WriteStatus> updateLocation(HoodieData<WriteStatus> writeStatuses, HoodieEngineContext context, HoodieTable hoodieTable) throws HoodieIndexException { + return writeStatuses; + } + + /** + * Do nothing. + * A failed write may create a hashing metadata for a partition. In this case, we still do nothing when rolling back + * the failed write. Because the hashing metadata created by a write must have 00000000000000 timestamp and can be viewed Review comment: Commits that don't modify the hashing metadata will reuse the latest valid metadata. So without split&merge, a complete write normally will not create new metadata unless it is doesn't exist. ps. split&merge (re-balancing) logic is not included in this pr. ########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/index/bucket/HoodieSparkConsistentBucketIndex.java ########## @@ -0,0 +1,218 @@ +/* + * 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.bucket; + +import org.apache.hudi.client.WriteStatus; +import org.apache.hudi.common.data.HoodieData; +import org.apache.hudi.common.engine.HoodieEngineContext; +import org.apache.hudi.common.fs.FSUtils; +import org.apache.hudi.common.fs.HoodieWrapperFileSystem; +import org.apache.hudi.common.model.ConsistentHashingNode; +import org.apache.hudi.common.model.HoodieConsistentHashingMetadata; +import org.apache.hudi.common.model.HoodieKey; +import org.apache.hudi.common.model.HoodieRecordLocation; +import org.apache.hudi.common.table.timeline.HoodieTimeline; +import org.apache.hudi.common.util.FileIOUtils; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieIOException; +import org.apache.hudi.exception.HoodieIndexException; +import org.apache.hudi.table.HoodieTable; + +import org.apache.hadoop.fs.FSDataOutputStream; +import org.apache.hadoop.fs.FileStatus; +import org.apache.hadoop.fs.Path; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; + +import java.io.IOException; +import java.util.Arrays; +import java.util.Comparator; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.function.Predicate; + +/** + * Consistent hashing bucket index implementation, with auto-adjust bucket number. + * NOTE: bucket resizing is triggered by clustering. + */ +public class HoodieSparkConsistentBucketIndex extends HoodieBucketIndex { + + private static final Logger LOG = LogManager.getLogger(HoodieSparkConsistentBucketIndex.class); + + private Map<String, ConsistentBucketIdentifier> partitionToIdentifier; Review comment: Sure! -- 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]
