hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "arkady borkovsky (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-1296) Improve interface to FileSystem.getFileCacheHints
Date Wed, 25 Apr 2007 18:51:15 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-1296?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12491728
] 

arkady borkovsky commented on HADOOP-1296:
------------------------------------------

Can this be extended to support wild cards (or rather all files in a directory) in single
call?

The actual "interesting objects" in DFS are blocks and directories, at least from MR perspective.
 
In most cases, the input to Map is all the blocks in the directory, files being transparent
artifacts.
So getting all the data needed to calculate the splits in a single call is quite logical.

> Improve interface to FileSystem.getFileCacheHints
> -------------------------------------------------
>
>                 Key: HADOOP-1296
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1296
>             Project: Hadoop
>          Issue Type: Improvement
>          Components: fs
>            Reporter: Owen O'Malley
>         Assigned To: dhruba borthakur
>
> The FileSystem interface provides a very limited interface for finding the location of
the data. The current method looks like:
> String[][] getFileCacheHints(Path file, long start, long len) throws IOException
> which returns a list of "block info" where the block info consists of a list host names.
Because the hints don't include the information about where the block boundaries are, map/reduce
is required to call the name node for each split. I'd propose that we fix the naming a bit
and make it:
> public class BlockInfo extends Writable {
>   public long getStart();
>   public String[] getHosts();
> }
> BlockInfo[] getFileHints(Path file, long start, long len) throws IOException;
> So that map/reduce can query about the entire file and get the locations in a single
call.

-- 
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