[ 
https://issues.apache.org/jira/browse/YARN-2928?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14337419#comment-14337419
 ] 

Gopal V commented on YARN-2928:
-------------------------------

The original discussion about ATS v1 drew inspiration from existing systems 
like rsyslog and scribe, which are simple systems which buffer/route/forward 
into a central store.

Those mechanisms were very useful in duplicating higher priority (and rare) 
events for immediate alerting/dashboards (errors/sec etc).

Are there any plans to include intermediate routing/forwarding systems for ATS 
v2?

The "tail -f | grep" firehose across a cluster is useful in avoiding 
scalability issues when looking for rare events in a distributed store.

Being able to route something like a node blacklisting event from an AppMaster 
to such a system would prevent the fault checker systems from having to produce 
irrelevant ATS traffic periodically to scrape through it.

> Application Timeline Server (ATS) next gen: phase 1
> ---------------------------------------------------
>
>                 Key: YARN-2928
>                 URL: https://issues.apache.org/jira/browse/YARN-2928
>             Project: Hadoop YARN
>          Issue Type: New Feature
>          Components: timelineserver
>            Reporter: Sangjin Lee
>            Assignee: Sangjin Lee
>            Priority: Critical
>         Attachments: ATSv2.rev1.pdf, ATSv2.rev2.pdf, Data model proposal 
> v1.pdf
>
>
> We have the application timeline server implemented in yarn per YARN-1530 and 
> YARN-321. Although it is a great feature, we have recognized several critical 
> issues and features that need to be addressed.
> This JIRA proposes the design and implementation changes to address those. 
> This is phase 1 of this effort.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to