hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Robert Chansler (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HDFS-385) Design a pluggable interface to place replicas of blocks in HDFS
Date Fri, 10 Jul 2009 01:00:15 GMT

    [ https://issues.apache.org/jira/browse/HDFS-385?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12729479#action_12729479
] 

Robert Chansler commented on HDFS-385:
--------------------------------------

Experiments with replica placement are important, and I want to read the resulting papers.
But a production implementation of an alternate policy has implications beyond just writing
a class that implements a new interface. Perhaps we need something like a [Black Box Warning|http://en.wikipedia.org/wiki/Black_box_warning]
to remind folk that using this feature to store real bytes is:

* Dangerous
* Really dangerous
* Not something that will be supported in the future if it stands in the way of other development
* Not something where others can be expected to volunteer help either to relieve the dangers
or cope with the consequences.



> Design a pluggable interface to place replicas of blocks in HDFS
> ----------------------------------------------------------------
>
>                 Key: HDFS-385
>                 URL: https://issues.apache.org/jira/browse/HDFS-385
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>            Reporter: dhruba borthakur
>            Assignee: dhruba borthakur
>             Fix For: 0.21.0
>
>         Attachments: BlockPlacementPluggable.txt, BlockPlacementPluggable2.txt, BlockPlacementPluggable3.txt,
BlockPlacementPluggable4.txt, BlockPlacementPluggable4.txt, BlockPlacementPluggable5.txt
>
>
> The current HDFS code typically places one replica on local rack, the second replica
on remote random rack and the third replica on a random node of that remote rack. This algorithm
is baked in the NameNode's code. It would be nice to make the block placement algorithm a
pluggable interface. This will allow experimentation of different placement algorithms based
on workloads, availability guarantees and failure models.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message