incubator-giraph-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Dmitriy V. Ryaboy (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (GIRAPH-28) Introduce new primitive-specific MutableVertex subclasses
Date Sun, 11 Sep 2011 23:30:09 GMT

    [ https://issues.apache.org/jira/browse/GIRAPH-28?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13102377#comment-13102377
] 

Dmitriy V. Ryaboy commented on GIRAPH-28:
-----------------------------------------

I tried to benchmark the memory footprint on this and was surprised to find that it's actually
larger than the existing implementation!

At Jake's suggestion, I also added a dummy "TinyVertex" that just does the simplest thing
possible, by keeping an array of primitives and resizing it when needed. This gives us the
lower bound on what our memory utilization could look like. The answer is, we could be 30x
more efficient in terms of memory utilization, at the cost of some CPU.

Code is here: https://gist.github.com/1210245

> Introduce new primitive-specific MutableVertex subclasses
> ---------------------------------------------------------
>
>                 Key: GIRAPH-28
>                 URL: https://issues.apache.org/jira/browse/GIRAPH-28
>             Project: Giraph
>          Issue Type: New Feature
>          Components: graph
>    Affects Versions: 0.70.0
>            Reporter: Jake Mannix
>            Assignee: Jake Mannix
>         Attachments: GIRAPH-28.diff
>
>
> As discussed on the list, MutableVertex<LongWritable,DoubleWritable,FloatWritable,DoubleWritable>
(for example) could be highly optimized in its memory footprint if the vertex and edge data
were held in a form which minimized Java object usage.

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

        

Mime
View raw message