Github user mridulm commented on a diff in the pull request:
https://github.com/apache/spark/pull/892#discussion_r13597675
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala ---
@@ -388,7 +386,7 @@ private[spark] class TaskSetManager(
val curTime = clock.getTime()
var allowedLocality = getAllowedLocalityLevel(curTime)
- if (allowedLocality > maxLocality) {
+ if (allowedLocality > maxLocality &&
myLocalityLevels.contains(maxLocality)) {
allowedLocality = maxLocality // We're not allowed to search for
farther-away tasks
--- End diff --
This is incorrect.
Consider this :
maxLocality == ANY, but allowedLocality == PROCESS_LOCAL (since sufficient
time has not elapsed for relaxing further) : and myLocalityLevels does not
contain process local executors.
Instead of not allowing any task to be executed; now we will allow
scheduling of tasks with ANY preference.
---
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.
---
