[
https://issues.apache.org/jira/browse/HAMA-704?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13580438#comment-13580438
]
Edward J. Yoon commented on HAMA-704:
-------------------------------------
{quote}The design should get things to work on 16GB 400 node cluster as well as
a 4GB 15 node cluster.{quote}
Suraj, I don't want to consider such extreme scenarios at the moment.
{quote}
Suraj: so I wanted to have a brief discussion about the whole matter
there is no escape .. we have to think about persisting the vertices outiside
main memory
4:51 PM
Suraj: that is why Thomas was thinking of making things Disk based.
{quote}
As I told you before, each Task loads 256MB vertices and uses 30GB memory. I
don't know why you think "disk-based vertices" is helpful? Memory usage is
continuously increased by vertex.setValue()?
> Optimization of memory usage during message processing
> ------------------------------------------------------
>
> Key: HAMA-704
> URL: https://issues.apache.org/jira/browse/HAMA-704
> Project: Hama
> Issue Type: Improvement
> Components: graph
> Reporter: Edward J. Yoon
> Assignee: Edward J. Yoon
> Priority: Critical
> Fix For: 0.6.1
>
> Attachments: hama-704_v05.patch, localdisk.patch, mytest.patch,
> patch.txt, patch.txt, removeMsgMap.patch
>
>
> <vertex, message> map seems consume a lot of memory. We should figure out an
> efficient way to reduce memory.
--
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
