[
https://issues.apache.org/jira/browse/MAPREDUCE-326?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12829710#action_12829710
]
Doug Cutting commented on MAPREDUCE-326:
----------------------------------------
Todd> If you want to actually look at the data, it doesn't really help much.
Good point. So maybe Java would take a performance hit. But the data wouldn't
need to deserialized. We'd need to compare it a few times. Ah, the rub.
Unless we mandate Avro compare and/or strcmp, comparison needs to be done in
user code. Sigh.
Todd> Is the assumption also that the InputFormat would run entirely in the
child process [ ... ]?
Yes.
Todd> How do we turn a dbinputformat split into a bytebuffer if the inputformat
lives on the child side?
The bytebuffer could contain the query. The child could execute that query.
> The lowest level map-reduce APIs should be byte oriented
> --------------------------------------------------------
>
> Key: MAPREDUCE-326
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-326
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Reporter: eric baldeschwieler
>
> As discussed here:
> https://issues.apache.org/jira/browse/HADOOP-1986#action_12551237
> The templates, serializers and other complexities that allow map-reduce to
> use arbitrary types complicate the design and lead to lots of object creates
> and other overhead that a byte oriented design would not suffer. I believe
> the lowest level implementation of hadoop map-reduce should have byte string
> oriented APIs (for keys and values). This API would be more performant,
> simpler and more easily cross language.
> The existing API could be maintained as a thin layer on top of the leaner API.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
