Details
-
New Feature
-
Status: Resolved
-
Major
-
Resolution: Incomplete
-
2.0.0
-
None
Description
Currently Spark on Yarn supports better data locality by considering the preferred locations of the pending tasks when dynamic allocation is enabled. Refer to https://issues.apache.org/jira/browse/SPARK-4352. It would be better that Mesos can also support this feature.
I guess that some logic existing in Yarn could be reused by Mesos.
Attachments
Issue Links
- is related to
-
SPARK-4352 Incorporate locality preferences in dynamic allocation requests
- Resolved
- links to