kevin85421 commented on code in PR #37411:
URL: https://github.com/apache/spark/pull/37411#discussion_r946374353
##########
core/src/main/scala/org/apache/spark/HeartbeatReceiver.scala:
##########
@@ -199,41 +241,120 @@ private[spark] class HeartbeatReceiver(sc: SparkContext,
clock: Clock)
removeExecutor(executorRemoved.executorId)
}
+ private def killExecutor(executorId: String, timeout: Long): Unit = {
+ logWarning(s"Removing executor $executorId with no recent heartbeats: " +
+ s"${timeout} ms exceeds timeout $executorTimeoutMs ms")
+ 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)
+ // SPARK-27348: in case of the executors which are not gracefully shut
down,
+ // we should remove lost executors from CoarseGrainedSchedulerBackend
manually
+ // here to guarantee two things:
+ // 1) explicitly remove executor information from
CoarseGrainedSchedulerBackend for
+ // a lost executor instead of waiting for disconnect message
+ // 2) call scheduler.executorLost() underlying to fail any tasks
assigned to
+ // those executors to avoid app hang
+ sc.schedulerBackend match {
+ case backend: CoarseGrainedSchedulerBackend =>
+ // TODO (SPARK-39984): Update causedByApp when we have a hanging
task detector
+ backend.driverEndpoint.send(RemoveExecutor(executorId,
+ ExecutorProcessLost(
+ s"Executor heartbeat timed out after ${timeout} ms")))
+ // LocalSchedulerBackend is used locally and only has one single
executor
+ case _: LocalSchedulerBackend =>
+
+ case other => throw new UnsupportedOperationException(
+ s"Unknown scheduler backend: ${other.getClass}")
+ }
+ }
+ })
+ }
+
+ private def isStandalone(): Boolean = {
+ sc.schedulerBackend match {
+ case backend: StandaloneSchedulerBackend => true
+ case _ => false
+ }
Review Comment:
Hi @Ngone51, thank you for your review!
Because `schedulerBackend` is possible to be None, I used pattern matching
instead of `isInstanceOf`. @mridulm and I have discussed the issues above. I
will tag you in these two discussion threads.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
