[ 
https://issues.apache.org/jira/browse/TEZ-1803?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Rajesh Balamohan updated TEZ-1803:
----------------------------------
    Attachment: TEZ-1803.5.patch

It is possible that the previous span had very limited capacity and ended up 
having length of 1.  In such scenarios, it is better to reinit completely.  
>>>
Span14.length = 1, perItem = 202
Span15.length = 1, perItem = 202
Span16.length = 1, perItem = 202
>>>

I have reduced the reinit codepath in the latest attachment.  Made minor 
changes to testcase as well.

> Support > 2gb sort buffer in pipelinedsorter
> --------------------------------------------
>
>                 Key: TEZ-1803
>                 URL: https://issues.apache.org/jira/browse/TEZ-1803
>             Project: Apache Tez
>          Issue Type: Bug
>            Reporter: Rajesh Balamohan
>            Assignee: Rajesh Balamohan
>              Labels: performance
>         Attachments: TEZ-1803.1.patch, TEZ-1803.2.patch, TEZ-1803.3.patch, 
> TEZ-1803.4.patch, TEZ-1803.5.patch, TEZ-1803.WIP.1.patch
>
>




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

Reply via email to