satishkotha commented on a change in pull request #2263: URL: https://github.com/apache/hudi/pull/2263#discussion_r532821349
########## File path: hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/table/action/cluster/SparkScheduleClusteringActionExecutor.java ########## @@ -0,0 +1,74 @@ +/* + * 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.table.action.cluster; + +import org.apache.hudi.avro.model.HoodieClusteringPlan; +import org.apache.hudi.client.WriteStatus; +import org.apache.hudi.client.common.HoodieEngineContext; +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.HoodieInstant; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.common.util.ReflectionUtils; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.table.HoodieTable; +import org.apache.hudi.table.action.cluster.strategy.ScheduleClusteringStrategy; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaRDD; + +import java.util.Map; + +@SuppressWarnings("checkstyle:LineLength") +public class SparkScheduleClusteringActionExecutor<T extends HoodieRecordPayload> extends + BaseScheduleClusteringActionExecutor<T, JavaRDD<HoodieRecord<T>>, JavaRDD<HoodieKey>, JavaRDD<WriteStatus>> { + + private static final Logger LOG = LogManager.getLogger(SparkScheduleClusteringActionExecutor.class); + + public SparkScheduleClusteringActionExecutor(HoodieEngineContext context, + HoodieWriteConfig config, + HoodieTable<T, JavaRDD<HoodieRecord<T>>, JavaRDD<HoodieKey>, JavaRDD<WriteStatus>> table, + String instantTime, + Option<Map<String, String>> extraMetadata) { + super(context, config, table, instantTime, extraMetadata); + } + + @Override + protected Option<HoodieClusteringPlan> scheduleClustering() { + LOG.info("Checking if clustering needs to be run on " + config.getBasePath()); + Option<HoodieInstant> lastClusteringInstant = table.getActiveTimeline().getCompletedReplaceTimeline().lastInstant(); + + int commitsSinceLastClustering = table.getActiveTimeline().getCommitsTimeline().filterCompletedInstants() + .findInstantsAfter(lastClusteringInstant.map(HoodieInstant::getTimestamp).orElse("0"), Integer.MAX_VALUE) + .countInstants(); + if (config.getInlineClusterMaxCommits() > commitsSinceLastClustering) { Review comment: I think this still makes sense for clustering too. Imagine, we are writing new data every 5minutes. It doesnt make sense to do file listing and figure out if theres enough data for clustering. User knows there is enough data after N minutes, so they can select N/5 commits here. We can also potentially move this to strategy specific implementation. But I do think most strategies will use this. Let me know if you want me to move this into strategy. ---------------------------------------------------------------- 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: [email protected]
