giraph-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jan van der Lugt (JIRA)" <>
Subject [jira] [Commented] (GIRAPH-297) Checkpointing on master is done one superstep later
Date Mon, 13 Aug 2012 17:47:38 GMT


Jan van der Lugt commented on GIRAPH-297:

This is expected: the at the end of superstep X, when the master aggregated the values, it
executes master.compute for X+1. This way, it logically executes _before_ the vertex.computes.
Since the master.compute is also executed at the end of input_superstep, the vertices have
the masters values at the beginning superstep 0. When I implemented this, aggregator values
were not checkpointed, I believe, so I did not think this would interfere with anything. Maybe
it's different now. I agree that this is not the most beautiful approach, but I tried various
and this was the only one I was able to get running (with master executing before the vertices
instead of after).
> Checkpointing on master is done one superstep later
> ---------------------------------------------------
>                 Key: GIRAPH-297
>                 URL:
>             Project: Giraph
>          Issue Type: Bug
>            Reporter: Maja Kabiljo
>            Assignee: Maja Kabiljo
> On workers we store checkpoint X before compute() for superstep X are executed. On master
we do it after those compute() are executed and after master.compute() for superstep X+1.

This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:!default.jspa
For more information on JIRA, see:


View raw message