spark-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From tdas <...@git.apache.org>
Subject [GitHub] spark pull request: [SPARK-1103] [WIP] Automatic garbage collectio...
Date Thu, 13 Mar 2014 05:05:10 GMT
Github user tdas commented on a diff in the pull request:

    https://github.com/apache/spark/pull/126#discussion_r10552879
  
    --- Diff: core/src/main/scala/org/apache/spark/ContextCleaner.scala ---
    @@ -0,0 +1,135 @@
    +/*
    + * 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}
    +
    +/** 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(sc: SparkContext) extends Logging {
    +
    +  /** Classes to represent cleaning tasks */
    +  private sealed trait CleaningTask
    +  private case class CleanRDD(rddId: Int) extends CleaningTask
    +  private case class CleanShuffle(shuffleId: 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() }}
    +
    +  @volatile private var stopped = false
    +
    +  /** Start the cleaner */
    +  def start() {
    +    cleaningThread.setDaemon(true)
    +    cleaningThread.start()
    +  }
    +
    +  /** Stop the cleaner */
    +  def stop() {
    +    stopped = true
    +    cleaningThread.interrupt()
    +  }
    +
    +  /**
    +   * Clean (unpersist) RDD data. Do not perform any time or resource intensive
    --- End diff --
    
    It could. But 2 reasons.
    1. I wanted to make sure that the code path accessed through the finalize is cheap (just
a queue insert with RDD ID) and independent of any other code paths.
    2. In future we may have other cleanups associated with RDD. Then they would be added
to doCleanRDD() rather than here. This code path of cleanRDD stays unaffected.


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message