[
https://issues.apache.org/jira/browse/GIRAPH-473?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13550335#comment-13550335
]
Alessandro Presta commented on GIRAPH-473:
------------------------------------------
If the test is supposed to check that local splits come first, it shouldn't
enforce anything stronger than that (in this case, a particular ordering on all
splits that will break whenever, say, the upstream hash function is changed).
The idea is that the test should break only if we introduce a bug/break a
contract, not if we change an implementation detail.
I'll fix it as part of this patch.
> InputSplitPathOrganizer should be aware of multiple threads
> -----------------------------------------------------------
>
> Key: GIRAPH-473
> URL: https://issues.apache.org/jira/browse/GIRAPH-473
> Project: Giraph
> Issue Type: Improvement
> Reporter: Alessandro Presta
> Assignee: Alessandro Presta
> Priority: Minor
> Attachments: GIRAPH-473.patch
>
>
> The starting offset for iterating over input splits is obtained by hashing
> the worker's hostname and port. When multiple input threads are used, they
> get the same offset.
> We should hash the thread id as well.
--
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
