[
https://issues.apache.org/jira/browse/HADOOP-4565?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12664777#action_12664777
]
Zheng Shao commented on HADOOP-4565:
------------------------------------
Nitpick:
CombineFileRecordReader seems to contain an unnecessary recursive call, which
can be easily eliminated.
{code}
public boolean next(K key, V value) throws IOException {
while ((curReader == null) || !curReader.next(key, value)) {
if (!initNextRecordReader()) {
return false;
}
}
return true;
}
{code}
I am OK with that we only use rack locality. I think most statistics have shown
that intra-rack communication is nearly free, especially when we are reading
big blocks of data.
> 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
> Attachments: CombineMultiFile.patch, CombineMultiFile2.patch,
> CombineMultiFile3.patch, CombineMultiFile4.patch, CombineMultiFile5.patch,
> CombineMultiFile7.patch
>
>
> 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.
