hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jothi Padmanabhan (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-4565) MultiFileInputSplit can use data locality information to create splits
Date Fri, 07 Nov 2008 09:06:44 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-4565?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12645719#action_12645719
] 

Jothi Padmanabhan commented on HADOOP-4565:
-------------------------------------------

bq. This requires that a JobClient has access to the network topology. A prerequisite is HADOOP-3293.

Did you mean, a prerequisite is HADOOP-4567 ? In HADOOP-3293, I am proposing to modify FileInputFormat.getSplits
to return the correct hosts during the creation of FileSplits(). Since MultFileInputFormat
overrides getSplits, it might be not able to use the changes in FileInputFormat.java. No?

> MultiFileInputSplit can use data locality information to create splits
> ----------------------------------------------------------------------
>
>                 Key: HADOOP-4565
>                 URL: https://issues.apache.org/jira/browse/HADOOP-4565
>             Project: Hadoop Core
>          Issue Type: Improvement
>          Components: mapred
>            Reporter: dhruba borthakur
>            Assignee: dhruba borthakur
>
> The MultiFileInputFormat takes a set of paths and creates splits based on file sizes.
Each splits contains a few files an each split are roughly equal in size. It would be efficient
if we can extend this InputFormat to create splits such each all the blocks in one split and
either node-local or rack-local.

-- 
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