all or nothing?

[Mark Kerzner <ma...@gmail.com>]

Hi,

MapReduce article mentions that one can tell MR how many machines to use for
the job, and then you can run multiple jobs on the cluster. I believe this
is not part of Hadoop, correct?

Thank you,
Mark

Re: all or nothing?

[Jason Venner <ja...@gmail.com>]

If you are using a version of hadoop that has a scheduler, which appeared in
19, you can provide scheduling domains that include subsets of the machines
in your cluster, otherwise jobs fill as much of the cluster and the cluster
resources are shared somewhat unevenly among all of the currently running
jobs.

On Thu, Dec 3, 2009 at 10:21 PM, Mark Kerzner <ma...@gmail.com> wrote:

> Hi,
>
> MapReduce article mentions that one can tell MR how many machines to use
> for
> the job, and then you can run multiple jobs on the cluster. I believe this
> is not part of Hadoop, correct?
>
> Thank you,
> Mark
>



-- 
Pro Hadoop, a book to guide you from beginner to hadoop mastery,
http://www.amazon.com/dp/1430219424?tag=jewlerymall
www.prohadoopbook.com a community for Hadoop Professionals