[ 
https://issues.apache.org/jira/browse/GIRAPH-45?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13150842#comment-13150842
 ] 

Jakob Homan commented on GIRAPH-45:
-----------------------------------

Cool.  I think we're all on the same page then.  No changes at the moment to 
the BSP model, but look at not saving all the messages to be sent until the end 
of the superstep.  One more reason I'd like to consider this is that our 
clusters are sensitive to spikes in usage; a 'shuffle' like megaswap of 
messages at the end of each superstep may not be the most friendly way to share 
multi-tenant clusters.  Giraph will probably be more welcome if it spreads its 
network usages across the whole processing pipeline.
                
> Improve the way to keep outgoing messages
> -----------------------------------------
>
>                 Key: GIRAPH-45
>                 URL: https://issues.apache.org/jira/browse/GIRAPH-45
>             Project: Giraph
>          Issue Type: Improvement
>          Components: bsp
>            Reporter: Hyunsik Choi
>            Assignee: Hyunsik Choi
>
> As discussed in GIRAPH-12(http://goo.gl/CE32U), I think that there is a 
> potential problem to cause out of memory when the rate of message generation 
> is higher than the rate of message flush (or network bandwidth).
> To overcome this problem, we need more eager strategy for message flushing or 
> some approach to spill messages into disk.
> The below link is Dmitriy's suggestion.
> https://issues.apache.org/jira/browse/GIRAPH-12?focusedCommentId=13116253&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-13116253

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: 
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Reply via email to