You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@hama.apache.org by "Edward J. Yoon (JIRA)" <ji...@apache.org> on 2012/12/07 02:05:20 UTC
[jira] [Commented] (HAMA-531) Data re-partitioning in BSPJobClient
[ https://issues.apache.org/jira/browse/HAMA-531?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13526058#comment-13526058 ]
Edward J. Yoon commented on HAMA-531:
-------------------------------------
I think the input partitioning issue should be handled at the BSP framework level. But, VertexInputReader hold back possibilities of integration. Since user can create their own InputFormatter, I don't think it's important feature.
Moreover, once partitioning-process separated from BSP computation, it will make able to specify desired number of tasks for graph job.
> Data re-partitioning in BSPJobClient
> ------------------------------------
>
> Key: HAMA-531
> URL: https://issues.apache.org/jira/browse/HAMA-531
> Project: Hama
> Issue Type: Improvement
> Reporter: Edward J. Yoon
> Priority: Critical
> Attachments: HAMA-531_1.patch, HAMA-531_2.patch, HAMA-531_final.patch
>
>
> The re-partitioning the data is a very expensive operation. By the way, currently, we processes read/write operations sequentially using HDFS api in BSPJobClient from client-side. This causes potential too many open files error, contains HDFS overheads, and shows slow performance.
> We have to find another way to re-partitioning data.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira