Github user tgravescs commented on a diff in the pull request:
https://github.com/apache/spark/pull/18150#discussion_r119736751
--- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
---
@@ -1383,19 +1394,43 @@ class DAGScheduler(
*/
private[scheduler] def handleExecutorLost(
execId: String,
- filesLost: Boolean,
- maybeEpoch: Option[Long] = None) {
+ workerLost: Boolean): Unit = {
+ // if the cluster manager explicitly tells us that the entire worker
was lost, then
+ // we know to unregister shuffle output. (Note that "worker"
specifically refers to the process
+ // from a Standalone cluster, where the shuffle service lives in the
Worker.)
+ val fileLost = workerLost ||
!env.blockManager.externalShuffleServiceEnabled
+ removeExecutorAndUnregisterOutputs(
+ execId = execId,
+ fileLost = fileLost,
+ hostToUnregisterOutputs = None,
+ maybeEpoch = None)
+ }
+
+ private def removeExecutorAndUnregisterOutputs(
+ execId: String,
+ fileLost: Boolean,
+ hostToUnregisterOutputs: Option[String],
+ maybeEpoch: Option[Long] = None): Unit = {
val currentEpoch = maybeEpoch.getOrElse(mapOutputTracker.getEpoch)
if (!failedEpoch.contains(execId) || failedEpoch(execId) <
currentEpoch) {
failedEpoch(execId) = currentEpoch
logInfo("Executor lost: %s (epoch %d)".format(execId, currentEpoch))
blockManagerMaster.removeExecutor(execId)
-
- if (filesLost || !env.blockManager.externalShuffleServiceEnabled) {
- logInfo("Shuffle files lost for executor: %s (epoch
%d)".format(execId, currentEpoch))
+ if (fileLost) {
+ hostToUnregisterOutputs match {
+ case Some(host) =>
+ logInfo("Shuffle files lost for host: %s (epoch
%d)".format(host, currentEpoch))
+ case None =>
+ logInfo("Shuffle files lost for executor: %s (epoch
%d)".format(execId, currentEpoch))
+ }
// TODO: This will be really slow if we keep accumulating shuffle
map stages
for ((shuffleId, stage) <- shuffleIdToMapStage) {
- stage.removeOutputsOnExecutor(execId)
+ hostToUnregisterOutputs match {
--- End diff --
so the thing I believe @joshrosen was talking about in the jira was instead
of invalidating all stages just invalidate the outputs for that mapSTage on
that host.
So something like for(all execs on failed host)
stage.removeOutputsOnExecutor(exec)
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
