incubator-hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Thomas Jungblut (JIRA)" <j...@apache.org>
Subject [jira] [Updated] (HAMA-423) Improve and Refactor Partitioning in the Examples
Date Fri, 19 Aug 2011 23:57:27 GMT

     [ https://issues.apache.org/jira/browse/HAMA-423?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Thomas Jungblut updated HAMA-423:
---------------------------------

    Attachment: HAMA-423-v1.patch

I really did a lot of stuff here.
But partitioning will now take about 1 minute for our example files.

I'm going to extend the wiki. Currently I am uploading the new .txt example files to trunk.

> Improve and Refactor Partitioning in the Examples
> -------------------------------------------------
>
>                 Key: HAMA-423
>                 URL: https://issues.apache.org/jira/browse/HAMA-423
>             Project: Hama
>          Issue Type: Improvement
>          Components: examples
>    Affects Versions: 0.3.0
>            Reporter: Thomas Jungblut
>            Assignee: Thomas Jungblut
>             Fix For: 0.4.0, 0.5.0
>
>         Attachments: HAMA-423-v1.patch
>
>
> Currently partitioning will write a key/value pair for each vertex/adjacent mapping.
> This results in heavy IO writes which actually bloats the file and let the partitioning
take unnecessarily long.
> We should partition directly into the vertex classes and implement a vertex list/array
writable which just writes a single key/value pair for a vertex/all-adjacents mapping.
> In fact we should make it generic, passing a vertex class which should implement the
Writable interface.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message