hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Tom White (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-4565) MultiFileInputSplit can use data locality information to create splits
Date Tue, 03 Feb 2009 09:02:06 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-4565?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12669898#action_12669898

Tom White commented on HADOOP-4565:


I was thinking that the asserts may need strengthening. For example, in the following code
(and other similar places) we should assert that the splits have the expected paths and locations.

// make sure that each split has different locations
for (int i = 0; i < splits.length; ++i) {
  CombineFileSplit fileSplit = (CombineFileSplit) splits[i];
  System.out.println("File split(Test1): " + fileSplit);
assertEquals(splits.length, 2);

Regarding HARs, I don't have a particular test in mind. We probably need a special input format
for HARs - that would be a separate issue. 

> 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
>             Fix For: 0.20.0, 0.21.0
>         Attachments: CombineMultiFile.patch, CombineMultiFile2.patch, CombineMultiFile3.patch,
CombineMultiFile4.patch, CombineMultiFile5.patch, CombineMultiFile7.patch, CombineMultiFile8.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.

View raw message