Github user Ngone51 commented on a diff in the pull request: https://github.com/apache/spark/pull/21486#discussion_r194606075 --- Diff: core/src/main/scala/org/apache/spark/HeartbeatReceiver.scala --- @@ -197,14 +197,14 @@ private[spark] class HeartbeatReceiver(sc: SparkContext, clock: Clock) if (now - lastSeenMs > executorTimeoutMs) { logWarning(s"Removing executor $executorId with no recent heartbeats: " + s"${now - lastSeenMs} ms exceeds timeout $executorTimeoutMs ms") - scheduler.executorLost(executorId, SlaveLost("Executor heartbeat " + - s"timed out after ${now - lastSeenMs} ms")) // Asynchronously kill the executor to avoid blocking the current thread killExecutorThread.submit(new Runnable { override def run(): Unit = Utils.tryLogNonFatalError { // Note: we want to get an executor back after expiring this one, // so do not simply call `sc.killExecutor` here (SPARK-8119) sc.killAndReplaceExecutor(executorId) --- End diff -- To be more specific, `killAndReplaceExecutor#killExecutors` will block until we get response from cluster manager or overtime after 120s (by default RPC timeout config).
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org