Github user pwendell commented on a diff in the pull request: https://github.com/apache/spark/pull/126#discussion_r11263139 --- Diff: core/src/main/scala/org/apache/spark/ContextCleaner.scala --- @@ -0,0 +1,196 @@ +/* + * 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 + +import java.lang.ref.{ReferenceQueue, WeakReference} + +import scala.collection.mutable.{ArrayBuffer, SynchronizedBuffer} + +import org.apache.spark.broadcast.Broadcast +import org.apache.spark.rdd.RDD + +/** + * Classes that represent cleaning tasks. + */ +private sealed trait CleanupTask +private case class CleanRDD(rddId: Int) extends CleanupTask +private case class CleanShuffle(shuffleId: Int) extends CleanupTask +private case class CleanBroadcast(broadcastId: Long) extends CleanupTask + +/** + * A WeakReference associated with a CleanupTask. + * + * When the referent object becomes only weakly reachable, the corresponding + * CleanupTaskWeakReference is automatically added to the given reference queue. + */ +private class CleanupTaskWeakReference( + val task: CleanupTask, + referent: AnyRef, + referenceQueue: ReferenceQueue[AnyRef]) + extends WeakReference(referent, referenceQueue) + +/** + * An asynchronous cleaner for RDD, shuffle, and broadcast state. + * + * This maintains a weak reference for each RDD, ShuffleDependency, and Broadcast of interest, + * to be processed when the associated object goes out of scope of the application. Actual + * cleanup is performed in a separate daemon thread. + */ +private[spark] class ContextCleaner(sc: SparkContext) extends Logging { + + private val referenceBuffer = new ArrayBuffer[CleanupTaskWeakReference] + with SynchronizedBuffer[CleanupTaskWeakReference] + + private val referenceQueue = new ReferenceQueue[AnyRef] + + private val listeners = new ArrayBuffer[CleanerListener] + with SynchronizedBuffer[CleanerListener] + + private val cleaningThread = new Thread() { override def run() { keepCleaning() }} + + @volatile private var stopped = false + + /** Attach a listener object to get information of when objects are cleaned. */ + def attachListener(listener: CleanerListener) { + listeners += listener + } + + /** Start the cleaner. */ + def start() { + cleaningThread.setDaemon(true) + cleaningThread.setName("ContextCleaner") --- End diff -- I'd say "Spark ContextCleaner" here since Spark programs have tons of threads from different libraries (akka, jetty, etc).
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. ---