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] [Commented] (HAMA-642) Make GraphRunner disk based
Date Thu, 18 Oct 2012 10:36:02 GMT

    [ https://issues.apache.org/jira/browse/HAMA-642?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13478892#comment-13478892
] 

Thomas Jungblut commented on HAMA-642:
--------------------------------------

Okay new requirements:

- linked structure on disk for iterating sequentially
- updates for vertices without requiring a certain alignment

If you assume that vertices always change if they are active, maybe it is better to write
the complete vertices in every superstep with their values etc.
The problem obviously is that this is like mapreduce without sorting.

However I think we can use a prefetch cache to preread vertices before the compute function,
so we can speedup the slow reads a bit.
                
> Make GraphRunner disk based
> ---------------------------
>
>                 Key: HAMA-642
>                 URL: https://issues.apache.org/jira/browse/HAMA-642
>             Project: Hama
>          Issue Type: Improvement
>          Components: graph
>    Affects Versions: 0.5.0
>            Reporter: Thomas Jungblut
>            Assignee: Thomas Jungblut
>         Attachments: HAMA-642_unix_1.patch, HAMA-642_unix_2.patch, HAMA-642_unix_3.patch,
HAMA-scale_1.patch, HAMA-scale_2.patch, HAMA-scale_3.patch, HAMA-scale_4.patch
>
>
> To improve scalability we can improve the graph runner to be disk based.
> Which basically means:
> - We have just a single Vertex instance that get's refilled.
> - We directly write vertices to disk after partitioning
> - In every superstep we iterate over the vertices on disk, fill the vertex instance and
call the users compute functions
> Problems:
> - State other than vertex value can't be stored easy
> - How do we deal with random access after messages have arrived?
> So I think we should make the graph runner more hybrid, like using the queues we have
implemented in the messaging. So the graphrunner can be configured to run completely on disk,
in cached mode or in in-memory mode.

--
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

Mime
View raw message