The temporary disk space limits should not skip jobs
----------------------------------------------------
Key: HADOOP-4306
URL: https://issues.apache.org/jira/browse/HADOOP-4306
Project: Hadoop Core
Issue Type: Bug
Components: mapred
Reporter: Owen O'Malley
In HADOOP-657, we added disk space modeling and throttling. The scheduler
currently picks the next job if there isn't enough space, which can lead to
starvation of jobs that require a lot of space. It should not schedule any task
if the first job can't use the space.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
