hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Matei Zaharia <ma...@eecs.berkeley.edu>
Subject Re: Global scheduling in the Fair Scheduler
Date Wed, 23 Dec 2009 01:42:25 GMT
Hi Abhishek,

You can find the in-development version of Hadoop in SVN, using the instructions at http://hadoop.apache.org/mapreduce/version_control.html.
Note that for version 0.21, the Hadoop project has been split into MapReduce, HDFS and Common,
which will make running the new version slightly trickier. There are some old instructions
about this at http://www.cloudera.com/blog/2009/07/17/the-project-split/, but I believe it's
gotten easier.

Note that you won't be able to use the 0.21 scheduler code in Hadoop 0.20 without manually
trying to port it though.


On Dec 22, 2009, at 7:23 PM, abhishek sharma wrote:

> Hi all,
> I want to use the Hadoop Fair Scheduler with Global scheduling feature.
> As per the following link,
> http://issues.apache.org/jira/browse/MAPREDUCE-548, Matei Zaharia has
> committed a patch for this as part of version 0.21.0.
> I believe version 0.21.0 is not released yet. However, is it possible
> for me to download the code related to the modified Fair Scheduler in
> order to use the global scheduling feature?
> Thanks,
> Abhishek

View raw message