cloud-fan commented on a change in pull request #29014:
URL: https://github.com/apache/spark/pull/29014#discussion_r460760991
##########
File path:
core/src/main/scala/org/apache/spark/scheduler/TaskSchedulerImpl.scala
##########
@@ -939,12 +941,43 @@ private[spark] class TaskSchedulerImpl(
override def executorDecommission(
executorId: String, decommissionInfo: ExecutorDecommissionInfo): Unit = {
+ synchronized {
+ // Don't bother noting decommissioning for executors that we don't know
about
+ if (executorIdToHost.contains(executorId)) {
+ // The scheduler can get multiple decommission updates from multiple
sources,
+ // and some of those can have isHostDecommissioned false. We merge
them such that
+ // if we heard isHostDecommissioned ever true, then we keep that one
since it is
+ // most likely coming from the cluster manager and thus authoritative
+ val oldDecomInfo = executorsPendingDecommission.get(executorId)
+ if (oldDecomInfo.isEmpty || !oldDecomInfo.get.isHostDecommissioned) {
+ executorsPendingDecommission(executorId) = decommissionInfo
+ }
+ }
+ }
rootPool.executorDecommission(executorId)
backend.reviveOffers()
}
- override def executorLost(executorId: String, reason: ExecutorLossReason):
Unit = {
+ override def getExecutorDecommissionInfo(executorId: String)
+ : Option[ExecutorDecommissionInfo] = synchronized {
+ executorsPendingDecommission.get(executorId)
+ }
+
+ override def executorLost(executorId: String, givenReason:
ExecutorLossReason): Unit = {
var failedExecutor: Option[String] = None
+ val reason = givenReason match {
+ // Handle executor process loss due to decommissioning
+ case ExecutorProcessLost(message, workerLost, causedByApp) =>
+ val executorDecommissionInfo = getExecutorDecommissionInfo(executorId)
+ ExecutorProcessLost(
+ message,
+ // Also mark the worker lost if we know that the host was
decommissioned
+ workerLost ||
executorDecommissionInfo.exists(_.isHostDecommissioned),
+ // Executor loss is certainly not caused by app if we knew that this
executor is being
+ // decommissioned
+ causedByApp = executorDecommissionInfo.isEmpty && causedByApp)
Review comment:
We add the `causedByApp` parameter, because we may decommission an
executor but not a host?
I'm thinking if `!workerLost` can indicate that the failure is caused by the
app.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
