[
https://issues.apache.org/jira/browse/HADOOP-3402?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12607668#action_12607668
]
Enis Soztutar commented on HADOOP-3402:
---------------------------------------
>From the patch :
{quote}
In May 2008, Owen O'Malley ran this code on a 910 node cluster and sorted the
10 billion records (1 TB) in 209 seconds (3.48 minutes).
{quote}
Wow !
Congratulations to the community. I believe it is very close to the world
record : http://www.hpl.hp.com/hosted/sortbenchmark/ (197 seconds)
Owen, we should list this in forrest documentation.
> Add example code to support run terasort on hadoop
> --------------------------------------------------
>
> Key: HADOOP-3402
> URL: https://issues.apache.org/jira/browse/HADOOP-3402
> Project: Hadoop Core
> Issue Type: New Feature
> Components: examples
> Reporter: Owen O'Malley
> Assignee: Owen O'Malley
> Attachments: terasort-2.patch, terasort.patch, terasort.patch
>
>
> It would be good to be able to run the terasort
> (http://www.hpl.hp.com/hosted/sortbenchmark/) on Hadoop. I need to write:
> * distributed data generator
> * sorter
> * result checker
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
