mgaido91 commented on a change in pull request #25643: [SPARK-28939][SQL] Propagate SQLConf for plans executed by toRdd URL: https://github.com/apache/spark/pull/25643#discussion_r321272374
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/SQLExecutionRDD.scala ########## @@ -0,0 +1,80 @@ +/* + * 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 + +import org.apache.spark.{Partition, TaskContext} +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.internal.SQLConf + +/** + * It is just a wrapper over `sqlRDD`, which sets and makes effective all the configs from the + * captured `SQLConf`. + * Please notice that this means we may miss configurations set after the creation of this RDD and + * before its execution. + * + * @param sqlRDD the `RDD` generated by the SQL plan + * @param conf the `SQLConf` to apply to the execution of the SQL plan + */ +class SQLExecutionRDD( + var sqlRDD: RDD[InternalRow], @transient conf: SQLConf) extends RDD[InternalRow](sqlRDD) { + private val sqlConfigs = conf.getAllConfs + @transient private var tasksRunning = 0 + @transient private var originalLocalProps: Map[String, String] = _ + + override val partitioner = firstParent[InternalRow].partitioner + + override def getPartitions: Array[Partition] = firstParent[InternalRow].partitions + + override def compute(split: Partition, context: TaskContext): Iterator[InternalRow] = { + // If we are in the context of a tracked SQL operation, `SQLExecution.EXECUTION_ID_KEY` is set + // and we have nothing to do here. Otherwise, we use the `SQLConf` captured at the creation of + // this RDD. + if (context.getLocalProperty(SQLExecution.EXECUTION_ID_KEY) == null) { + synchronized { + if (tasksRunning == 0) { Review comment: yes, I'd say so. ---------------------------------------------------------------- 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 --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
