wangshuo128 commented on a change in pull request #27248: [WIP][SPARK-20538][SQL] Control spark sql output small file by merge small partition URL: https://github.com/apache/spark/pull/27248#discussion_r368264472
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/SizeBasedCoalescer.scala ########## @@ -0,0 +1,77 @@ +/* + * 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.spark.sql.execution.datasources + +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.Partition +import org.apache.spark.rdd._ +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.catalyst.plans.logical.statsEstimation.EstimationUtils + +class SizeBasedCoalescer(val maxSize: Long, val schema: Seq[Attribute]) + extends PartitionCoalescer with Serializable { + override def coalesce(maxPartitions: Int, parent: RDD[_]): Array[PartitionGroup] = { + val rowSize = EstimationUtils.getSizePerRow(schema).toLong + val partitionIndexToSize = parent.mapPartitionsWithIndexInternal((index, part) => { + // TODO make it more accurate + Map(index -> rowSize * part.size).iterator + }).collectAsMap() Review comment: Is it too costly to trigger an action to compute all the RDDs? ---------------------------------------------------------------- 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] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
