Github user vanzin commented on a diff in the pull request: https://github.com/apache/spark/pull/9963#discussion_r46459294 --- Diff: core/src/main/scala/org/apache/spark/scheduler/cluster/CoarseGrainedSchedulerBackend.scala --- @@ -341,6 +341,25 @@ class CoarseGrainedSchedulerBackend(scheduler: TaskSchedulerImpl, val rpcEnv: Rp } } + /** + * Reset the state of CoarseGrainedSchedulerBackend to the initial state. Currently it will only + * be called in the yarn-client mode when AM re-registers after a failure, also dynamic + * allocation is enabled. + * */ + protected def reset(): Unit = synchronized { + if (Utils.isDynamicAllocationEnabled(conf)) { + numPendingExecutors = 0 + executorsPendingToRemove.clear() + + // Remove all the lingering executors that should be removed but not yet. The reason might be + // because (1) disconnected event is not yet received; (2) executors die silently. + executorDataMap.toMap.foreach { case (eid, _) => + driverEndpoint.askWithRetry[Boolean]( + RemoveExecutor(eid, SlaveLost("State executor after cluster manager re-registered"))) --- End diff -- "Stale", missing period.
--- 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