NNBench could be improved
-------------------------
Key: HADOOP-3538
URL: https://issues.apache.org/jira/browse/HADOOP-3538
Project: Hadoop Core
Issue Type: Bug
Components: test
Affects Versions: 0.19.0
Reporter: Lohit Vijayarenu
Priority: Minor
It would be good to change NNBench a bit
- numberOfFiles is actually number of files per mapper. It would be good to
document it
- right now, we have to kick off separate jobs for each operations. Since we
operate on same generated files, it would be good to have an option of all
operations or chain selected operations
- It would be good to see if we can kick off all operations in parallel to
simulate the usual NameNode state
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
