[
https://issues.apache.org/jira/browse/MAPREDUCE-3202?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
vitthal (Suhas) Gogate updated MAPREDUCE-3202:
----------------------------------------------
Summary: Integrating Hadoop Vaidya with Job History UI in Hadoop 2.0
(was: Integrating Hadoop Vaidya with JobHistory Server)
> Integrating Hadoop Vaidya with Job History UI in Hadoop 2.0
> ------------------------------------------------------------
>
> Key: MAPREDUCE-3202
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3202
> Project: Hadoop Map/Reduce
> Issue Type: New Feature
> Components: jobhistoryserver
> Affects Versions: 0.20.205.0, 1.0.0
> Reporter: vitthal (Suhas) Gogate
>
> At present jobdetailshistory page served by JobHistory Server provides
> elementary job analysis through link "Analyze This job". Hadoop Vaidya
> provides a detailed analysis of the M/R job in terms of various execution
> inefficiencies and the associated remedies that user can easily understand
> and fix. Integrating Hadoop Vaidya with JobHistory server would really
> improve the usability of this tool and also benefit many naive users
> understanding various performance problems and/or best practices violations
> associated with their job.
> Integration would also aim at providing users a convenient interface where
> they can manage the existing rules as well as write their own new rules.
> During my tenure at Yahoo, Vaidya tool was successfully deployed in
> production analyzing tens of thousands of jobs every day with lot more useful
> rules than the sample ones present in the contrib project. Many of these
> rules are open sourced already (big thanks to Yahoo! MAPREDUCE-1530) but yet
> to integrate with the tool.
> I will add more design details for this feature in near future as work
> towards getting prototype running.. Any thoughts/comments are welcome.
--
This message was sent by Atlassian JIRA
(v6.1#6144)
