[
https://issues.apache.org/jira/browse/HAMA-974?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14734276#comment-14734276
]
Edward J. Yoon commented on HAMA-974:
-------------------------------------
{quote}so the the previous messages, etc. can be put back in iteration{quote}
Is that a chainable superstep API? Anyway, it looks like a different story from
checkpointing local variables (should be manually handled by user), such as
vertices and its values. So, it's not a duplicated.
> Support fault tolerance for Graph job
> -------------------------------------
>
> Key: HAMA-974
> URL: https://issues.apache.org/jira/browse/HAMA-974
> Project: Hama
> Issue Type: Improvement
> Components: graph
> Affects Versions: 0.7.0
> Reporter: Edward J. Yoon
> Fix For: 0.8.0
>
>
> Currently we only checkpoints messages. To support FT for graph job,
> aggregators, assigned vertices and its statuses must be checkpointed together.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
