hadoop-common-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Colin Patrick McCabe (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HADOOP-9689) Implement HDFS Zero-copy reading
Date Wed, 03 Jul 2013 01:15:20 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-9689?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13698472#comment-13698472
] 

Colin Patrick McCabe commented on HADOOP-9689:
----------------------------------------------

Hi Jacques,

I've been working on a patch that enables mmap support in HDFS.  I'm going to post it this
week.

Since you mentioned HADOOP-8148, I assume that the zero-copy work you're doing here relates
to eliminating the buffer copies in the decompression codecs by replacing byte[] copies with
the use of ByteBuffer and so forth.  If you are also working on mmap, let's coordinate on
HDFS-4953.

You might also want to remove the 'HDFS' from the title if this JIRA is in Hadoop common...
or move it to HDFS. :)

C.
                
> Implement HDFS Zero-copy reading
> --------------------------------
>
>                 Key: HADOOP-9689
>                 URL: https://issues.apache.org/jira/browse/HADOOP-9689
>             Project: Hadoop Common
>          Issue Type: New Feature
>            Reporter: Jacques Nadeau
>
> Leverage the work in https://issues.apache.org/jira/browse/HADOOP-8148 to support zero
copy reading of columnar file formats for improved performance.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message