Github user andrewor14 commented on a diff in the pull request:

    https://github.com/apache/spark/pull/126#discussion_r10551095
  
    --- Diff: core/src/main/scala/org/apache/spark/ContextCleaner.scala ---
    @@ -0,0 +1,126 @@
    +/*
    + * 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 scala.collection.mutable.{ArrayBuffer, SynchronizedBuffer}
    +
    +import java.util.concurrent.{LinkedBlockingQueue, TimeUnit}
    +
    +import org.apache.spark.rdd.RDD
    +
    +/** Listener class used for testing when any item has been cleaned by the 
Cleaner class */
    +private[spark] trait CleanerListener {
    +  def rddCleaned(rddId: Int)
    +  def shuffleCleaned(shuffleId: Int)
    +}
    +
    +/**
    + * Cleans RDDs and shuffle data.
    + */
    +private[spark] class ContextCleaner(env: SparkEnv) extends Logging {
    +
    +  /** Classes to represent cleaning tasks */
    +  private sealed trait CleaningTask
    +  private case class CleanRDD(sc: SparkContext, id: Int) extends 
CleaningTask
    +  private case class CleanShuffle(id: Int) extends CleaningTask
    +  // TODO: add CleanBroadcast
    +
    +  private val queue = new LinkedBlockingQueue[CleaningTask]
    +
    +  protected val listeners = new ArrayBuffer[CleanerListener]
    +    with SynchronizedBuffer[CleanerListener]
    +
    +  private val cleaningThread = new Thread() { override def run() { 
keepCleaning() }}
    +
    +  private var stopped = false
    +
    +  /** Start the cleaner */
    +  def start() {
    +    cleaningThread.setDaemon(true)
    +    cleaningThread.start()
    +  }
    +
    +  /** Stop the cleaner */
    +  def stop() {
    +    synchronized { stopped = true }
    +    cleaningThread.interrupt()
    +  }
    +
    +  /** Clean (unpersist) RDD data. */
    +  def cleanRDD(rdd: RDD[_]) {
    +    enqueue(CleanRDD(rdd.sparkContext, rdd.id))
    +    logDebug("Enqueued RDD " + rdd + " for cleaning up")
    +  }
    +
    +  /** Clean shuffle data. */
    +  def cleanShuffle(shuffleId: Int) {
    +    enqueue(CleanShuffle(shuffleId))
    +    logDebug("Enqueued shuffle " + shuffleId + " for cleaning up")
    +  }
    +
    +  def attachListener(listener: CleanerListener) {
    +    listeners += listener
    +  }
    +  /** Enqueue a cleaning task */
    +  private def enqueue(task: CleaningTask) {
    +    queue.put(task)
    +  }
    +
    +  /** Keep cleaning RDDs and shuffle data */
    +  private def keepCleaning() {
    +    try {
    +      while (!isStopped) {
    +        val taskOpt = Option(queue.poll(100, TimeUnit.MILLISECONDS))
    --- End diff --
    
    By configurable I don't mean exposing it to the user. It just seems to be 
that 100ms is completely arbitrary and it would be good to at least have a 
mechanism to change it.


---
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.
---

Reply via email to