Details
-
Bug
-
Status: Closed
-
Major
-
Resolution: Fixed
-
0.9.0
-
None
-
None
-
None
Description
The job tracker currently runs out of memory when a user runs a lot of small jobs back to back. To bound the amount of RAM that the job tracker consumes recording completed/failed jobs, I think that the JobTracker should limit the number of "remembered" jobs per a user to jobtracker.max.remembered.task.per.user (default 100).
Attachments
Issue Links
- is part of
-
HADOOP-815 Investigate and fix the extremely large memory-footprint of JobTracker
- Closed