[
https://issues.apache.org/jira/browse/HDFS-236?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13046572#comment-13046572
]
Kihwal Lee commented on HDFS-236:
---------------------------------
* Some test.io.randomread.* seem to deserve a spot in command line args.
* The buffer size can be used as the read size in random reads. I see no reason
to separate the two in the random read mode.
* The default behavior is, one random reader operates on just one file out of N
files. Since it already has ability to limit the number of files that each
reader can access, it might be better to make it work on all N files by default.
> Random read benchmark for DFS
> -----------------------------
>
> Key: HDFS-236
> URL: https://issues.apache.org/jira/browse/HDFS-236
> Project: Hadoop HDFS
> Issue Type: New Feature
> Reporter: Raghu Angadi
> Assignee: Raghu Angadi
> Attachments: HDFS-236.patch, RndRead-TestDFSIO.patch
>
>
> We should have at least one random read benchmark that can be run with rest
> of Hadoop benchmarks regularly.
> Please provide benchmark ideas or requirements.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
