Github user aarondav commented on a diff in the pull request: https://github.com/apache/spark/pull/1486#discussion_r17769055 --- Diff: core/src/main/scala/org/apache/spark/scheduler/TaskLocation.scala --- @@ -22,13 +22,35 @@ package org.apache.spark.scheduler * In the latter case, we will prefer to launch the task on that executorID, but our next level * of preference will be executors on the same host if this is not possible. */ -private[spark] -class TaskLocation private (val host: String, val executorId: Option[String]) extends Serializable { - override def toString: String = "TaskLocation(" + host + ", " + executorId + ")" +private[spark] sealed abstract class TaskLocation(val host: String) { +} + +private [spark] case class ExecutorCacheTaskLocation(override val host: String, + val executorId: String) extends TaskLocation(host) { +} + +private [spark] case class HDFSCachedTaskLocation(override val host: String) + extends TaskLocation(host) { + override def toString = TaskLocation.in_memory_location_tag + host +} + +private [spark] case class HostTaskLocation(override val host: String) extends TaskLocation(host) { + override def toString = host } private[spark] object TaskLocation { - def apply(host: String, executorId: String) = new TaskLocation(host, Some(executorId)) + // We identify hosts on which the block is cached with this prefix. Because this prefix contains + // underscores, which are not legal characters in hostnames, there should be no potential for + // confusion. See RFC 952 and RFC 1123 for information about the format of hostnames. + val in_memory_location_tag = "_hdfs_cache_" + + def apply(host: String, executorId: String) = new ExecutorCacheTaskLocation(host, executorId) - def apply(host: String) = new TaskLocation(host, None) + def apply(str: String) = { + if (str.startsWith(in_memory_location_tag)) { + new HDFSCachedTaskLocation(str.substring(in_memory_location_tag.length)) --- End diff -- nit: `str.stripPrefix(in_memory_location_tag)`
--- 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