[ 
https://issues.apache.org/jira/browse/MAPREDUCE-7073?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Bibin A Chundatt updated MAPREDUCE-7073:
----------------------------------------
    Description: 
{{FileInputFormat#listStatus}} is too slow file system cache is disabled. 

{{TokenCache#obtainTokensForNamenodesInternal}} for every filesystem instance 
{{Master.getMasterPrincipal(conf)}} is caled which reloads YarnConfiguration .
For fileInput with 1k file will reload YarnConfiguration 1k times.

{{Master.getMasterPrincipal(conf)}} can be passed for  
{{obtainTokensForNamenodesInternal}} per filesystem call.


  was:
{{FileInputFormat#listStatus}} is too slow file system cache is disabled. 

{{TokenCache#obtainTokensForNamenodesInternal}} for every filesystem instance 
{{Master.getMasterPrincipal(conf)}} is caled which reloads YarnConfiguration .
For fileInput with 1k file will reload YarnConfiguration 1k times.

{{Master.getMasterPrincipal(conf)}} can be passed for  
{{obtainTokensForNamenodesInternal}} per filesystem call.


> Optimize TokenCache#obtainTokensForNamenodesInternal
> ----------------------------------------------------
>
>                 Key: MAPREDUCE-7073
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-7073
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>            Reporter: Bibin A Chundatt
>            Assignee: Bibin A Chundatt
>            Priority: Major
>         Attachments: MAPREDUCE-7073.001.patch
>
>
> {{FileInputFormat#listStatus}} is too slow file system cache is disabled. 
> {{TokenCache#obtainTokensForNamenodesInternal}} for every filesystem instance 
> {{Master.getMasterPrincipal(conf)}} is caled which reloads YarnConfiguration .
> For fileInput with 1k file will reload YarnConfiguration 1k times.
> {{Master.getMasterPrincipal(conf)}} can be passed for  
> {{obtainTokensForNamenodesInternal}} per filesystem call.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

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

Reply via email to