You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@tinkerpop.apache.org by "Marko A. Rodriguez (JIRA)" <ji...@apache.org> on 2015/04/07 17:15:13 UTC

[jira] [Commented] (TINKERPOP3-595) Verify GiraphGraphComputer and SparkGraphComputer at scale.

    [ https://issues.apache.org/jira/browse/TINKERPOP3-595?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14483338#comment-14483338 ] 

Marko A. Rodriguez commented on TINKERPOP3-595:
-----------------------------------------------

[~dkuppitz] and I have shown {{SparkGraphComputer}} at scale. It performed well with Friendster (2.5 billion edges) on 3 Blades. I believe that the message passing algorithm is solid, now we just need to make sure we can hold more of it in memory. This entails finishing up the following tickets: TINKERPOP3-609 and TINKERPOP3-613.

> Verify GiraphGraphComputer and SparkGraphComputer at scale.
> -----------------------------------------------------------
>
>                 Key: TINKERPOP3-595
>                 URL: https://issues.apache.org/jira/browse/TINKERPOP3-595
>             Project: TinkerPop 3
>          Issue Type: Improvement
>          Components: hadoop, process
>            Reporter: Marko A. Rodriguez
>             Fix For: 3.0.0.GA
>
>




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