Github user holdenk commented on a diff in the pull request: https://github.com/apache/spark/pull/11140#discussion_r52374340 --- Diff: core/src/main/scala/org/apache/spark/api/python/PythonRDD.scala --- @@ -892,27 +911,31 @@ private[spark] class PythonBroadcast(@transient var path: String) extends Serial private def readObject(in: ObjectInputStream): Unit = Utils.tryOrIOException { val dir = new File(Utils.getLocalDir(SparkEnv.get.conf)) val file = File.createTempFile("broadcast", "", dir) + + phantomReferences += new FilePhantomReference(file,queue) + path = file.getAbsolutePath val out = new FileOutputStream(file) Utils.tryWithSafeFinally { Utils.copyStream(in, out) } { - out.close() + in.close(); } } - - /** - * Delete the file once the object is GCed. - */ - override def finalize() { - if (!path.isEmpty) { - val file = new File(path) - if (file.exists()) { - if (!file.delete()) { - logWarning(s"Error deleting ${file.getPath}") + /** Create a seperate daemon thread to remove phantomreferences from queue and invoke cleanup */ + + val referenceThread= new Thread { + setDaemon(true) + override def run() { + try { + val ref=queue.remove().asInstanceOf[FilePhantomReference] + phantomReferences-=ref + + } catch{ + case e: Exception => logError(s"Error removing reference",e) } } - } - } + }.start() + --- End diff -- whitespace
--- 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. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org