AngersZhuuuu commented on a change in pull request #27983: URL: https://github.com/apache/spark/pull/27983#discussion_r449953990
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/script/ScriptTransformbase.scala ########## @@ -0,0 +1,167 @@ +/* + * 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.script + +import java.io.OutputStream +import java.util.concurrent.TimeUnit + +import scala.util.control.NonFatal + +import org.apache.hadoop.conf.Configuration + +import org.apache.spark.{SparkException, TaskContext} +import org.apache.spark.internal.Logging +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.UnsafeProjection +import org.apache.spark.sql.execution.UnaryExecNode +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.DataType +import org.apache.spark.util.{CircularBuffer, SerializableConfiguration, Utils} + +trait ScriptTransformBase extends UnaryExecNode { + override def doExecute(): RDD[InternalRow] = { + val broadcastedHadoopConf = + new SerializableConfiguration(sqlContext.sessionState.newHadoopConf()) + + child.execute().mapPartitions { iter => + if (iter.hasNext) { + val proj = UnsafeProjection.create(schema) + processIterator(iter, broadcastedHadoopConf.value).map(proj) + } else { + // If the input iterator has no rows then do not launch the external script. + Iterator.empty + } + } + } + + def processIterator( + inputIterator: Iterator[InternalRow], + hadoopConf: Configuration): Iterator[InternalRow] + + protected def checkFailureAndPropagate( + writerThread: ScriptTransformationWriterThreadBase, + cause: Throwable = null, + proc: Process, + stderrBuffer: CircularBuffer): Unit = { + if (writerThread.exception.isDefined) { + throw writerThread.exception.get + } + + // There can be a lag between reader read EOF and the process termination. + // If the script fails to startup, this kind of error may be missed. + // So explicitly waiting for the process termination. + val timeout = conf.getConf(SQLConf.SCRIPT_TRANSFORMATION_EXIT_TIMEOUT) + val exitRes = proc.waitFor(timeout, TimeUnit.SECONDS) + if (!exitRes) { + log.warn(s"Transformation script process exits timeout in $timeout seconds") + } + + if (!proc.isAlive) { + val exitCode = proc.exitValue() + if (exitCode != 0) { + logError(stderrBuffer.toString) // log the stderr circular buffer + throw new SparkException(s"Subprocess exited with status $exitCode. " + + s"Error: ${stderrBuffer.toString}", cause) + } + } + } +} + +abstract class ScriptTransformationWriterThreadBase( Review comment: > ditto: `ScriptTransformationWriterThreadBase` -> `BaseScriptTransformationWriterThread` Yea， also `ScriptTransformIOSchemaBase` -> `BaseScriptTransformIOSchema` ---------------------------------------------------------------- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
