Github user sitalkedia commented on a diff in the pull request:
https://github.com/apache/spark/pull/17088#discussion_r106774060
--- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
---
@@ -1390,7 +1401,34 @@ class DAGScheduler(
}
} else {
logDebug("Additional executor lost message for " + execId +
- "(epoch " + currentEpoch + ")")
+ "(epoch " + currentEpoch + ")")
+ }
+ }
+
+ private[scheduler] def removeExecutorAndUnregisterOutputOnHost(
+ execId: String,
+ host: String,
+ maybeEpoch: Option[Long] = None) {
+ 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)
+ for ((shuffleId, stage) <- shuffleIdToMapStage) {
+ logInfo("Shuffle files lost for host: %s (epoch %d)".format(host,
currentEpoch))
+ stage.removeOutputsOnHost(host)
+ mapOutputTracker.registerMapOutputs(
+ shuffleId,
+ stage.outputLocInMapOutputTrackerFormat(),
+ changeEpoch = true)
+ }
+ if (shuffleIdToMapStage.isEmpty) {
+ mapOutputTracker.incrementEpoch()
+ }
+ clearCacheLocs()
+ } else {
+ logDebug("Additional executor lost message for " + execId +
+ "(epoch " + currentEpoch + ")")
--- End diff --
Made changes as suggested, thanks!
---
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
