hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Avner BenHanoch (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (MAPREDUCE-4049) plugin for generic shuffle service
Date Sun, 09 Dec 2012 14:39:28 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-4049?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13527482#comment-13527482
] 

Avner BenHanoch commented on MAPREDUCE-4049:
--------------------------------------------


If you need more:
 * My issue is a PART OF whole new topic of Shuffle Consumer – Shuffle Provider plugins.
 Currently, we just submitted the consumer part.  We still need to complete *the provider
part* in MRv2 and in MRv1, plus few related topics.  Then we need to back port all to hadoop-2
& hadoop-1.

 * Hence, my issue is part of other big context and not part of your issue (Still, be my guest,
and feel free to subordinate your issue to my issue)

 * Besides, it was already clearly said that at any case, MAPREDUCE-2454 can’t be accepted
to hadoop-1, since it is too massive change for a branch that is going to its end of life.
 On the other hand, my patch already passed code review for hadoop-1 and was only delayed
because of a justified request to go in the regular path and first submit to trunk.  Hence,
there is no reason to block my trivial patch for all branches just because the complex issues
in MAPREDUCE-2454.

                
> plugin for generic shuffle service
> ----------------------------------
>
>                 Key: MAPREDUCE-4049
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4049
>             Project: Hadoop Map/Reduce
>          Issue Type: Sub-task
>          Components: performance, task, tasktracker
>    Affects Versions: 1.0.3, 1.1.0, 2.0.0-alpha, 3.0.0
>            Reporter: Avner BenHanoch
>            Assignee: Avner BenHanoch
>              Labels: merge, plugin, rdma, shuffle
>             Fix For: 3.0.0
>
>         Attachments: HADOOP-1.x.y.patch, Hadoop Shuffle Plugin Design.rtf, mapreduce-4049.patch,
mapreduce-4049.patch, mapreduce-4049.patch, mapreduce-4049.patch, mapreduce-4049.patch, mapreduce-4049.patch
>
>
> Support generic shuffle service as set of two plugins: ShuffleProvider & ShuffleConsumer.
> This will satisfy the following needs:
> # Better shuffle and merge performance. For example: we are working on shuffle plugin
that performs shuffle over RDMA in fast networks (10gE, 40gE, or Infiniband) instead of using
the current HTTP shuffle. Based on the fast RDMA shuffle, the plugin can also utilize a suitable
merge approach during the intermediate merges. Hence, getting much better performance.
> # Satisfy MAPREDUCE-3060 - generic shuffle service for avoiding hidden dependency of
NodeManager with a specific version of mapreduce shuffle (currently targeted to 0.24.0).
> References:
> # Hadoop Acceleration through Network Levitated Merging, by Prof. Weikuan Yu from Auburn
University with others, [http://pasl.eng.auburn.edu/pubs/sc11-netlev.pdf]
> # I am attaching 2 documents with suggested Top Level Design for both plugins (currently,
based on 1.0 branch)
> # I am providing link for downloading UDA - Mellanox's open source plugin that implements
generic shuffle service using RDMA and levitated merge.  Note: At this phase, the code is
in C++ through JNI and you should consider it as beta only.  Still, it can serve anyone that
wants to implement or contribute to levitated merge. (Please be advised that levitated merge
is mostly suit in very fast networks) - [http://www.mellanox.com/content/pages.php?pg=products_dyn&product_family=144&menu_section=69]

--
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

Mime
View raw message