[ 
https://issues.apache.org/jira/browse/YARN-5955?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15721355#comment-15721355
 ] 

zhangyubiao edited comment on YARN-5955 at 12/5/16 8:53 AM:
------------------------------------------------------------

[~templedf], is it zookeeper is the best way to store the app state? is it can 
improve good enough performance to the large cluster to recovery apps?
 as we [~tangshangwen] [~zhengchenyu] see in  
http://www.slideshare.net/arinto/next-generation-hadoop-high-availability-for-yarn.
 it seem like that zookeeper is not the best way to store the app state.
[~Naganarasimha]  [~varun_saxena]  [~rohithsharma]


was (Author: piaoyu zhang):
[~templedf], is it zookeeper is the best way to store the app state? is it can 
improve performance to the large cluster to recovery apps?
 as we [~tangshangwen] [~zhengchenyu] see in  
http://www.slideshare.net/arinto/next-generation-hadoop-high-availability-for-yarn.
 it seem like that zookeeper is not the best way to store the app state.
[~Naganarasimha]  [~varun_saxena]  [~rohithsharma]

> Use threadpool or multiple thread to recover app
> ------------------------------------------------
>
>                 Key: YARN-5955
>                 URL: https://issues.apache.org/jira/browse/YARN-5955
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: resourcemanager
>    Affects Versions: 2.7.1
>            Reporter: Zhaofei Meng
>            Assignee: Ajith S
>             Fix For: 2.7.1
>
>
> current app recovery is one by one,use thead pool can make recovery faster.



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

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org

Reply via email to