You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-dev@hadoop.apache.org by "Hairong Kuang (JIRA)" <ji...@apache.org> on 2006/09/01 22:51:23 UTC
[jira] Updated: (HADOOP-499) Avoid the use of Strings to improve
the performance of hadoop streaming
[ http://issues.apache.org/jira/browse/HADOOP-499?page=all ]
Hairong Kuang updated HADOOP-499:
---------------------------------
Attachment: text_streaming.patch
This patch includes the following fix:
1. replace the the use of UTF8 by Text in hadoop-streaming. Therefore, it fixesADOOP-413.
2. removes the use of stringsby adding simple manipulation of bytes arrays.
3. fix the stream close order when map/reduce finishes hence avoid truncated records.
> Avoid the use of Strings to improve the performance of hadoop streaming
> ------------------------------------------------------------------------
>
> Key: HADOOP-499
> URL: http://issues.apache.org/jira/browse/HADOOP-499
> Project: Hadoop
> Issue Type: Improvement
> Components: contrib/streaming
> Affects Versions: 0.5.0
> Reporter: Hairong Kuang
> Assigned To: Hairong Kuang
> Fix For: 0.6.0
>
> Attachments: text_streaming.patch
>
>
> In hadoop streaming, a record is represented as a String for I/O and is encoded as UTF8 for map/reduce. A record has to be converted between String and UTF8 back and forth multiple times and this wastes CPU time.
--
This message is automatically generated by JIRA.
-
If you think it was sent incorrectly contact one of the administrators: http://issues.apache.org/jira/secure/Administrators.jspa
-
For more information on JIRA, see: http://www.atlassian.com/software/jira