hadoop-mapreduce-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Harsh J <qwertyman...@gmail.com>
Subject Re: Scheduler in Hadoop MR
Date Wed, 08 Dec 2010 02:47:32 GMT
Hi,

Replies inline.

On Tue, Dec 7, 2010 at 8:07 PM,  <psdc1978@gmail.com> wrote:
> Hi,
>
> I'm trying to understand how the scheduler works in the Hadoop MR, and I've
> got the following questions:
>
> 1 - When we've two JobTrackers running simultaneously, each JobTracker is
> running in a separate process?

You can't run simultaneous JobTrackers for the same data-cluster
AFAIK; only one JT process can exist. Did you mean jobs?

>
> 2 - The default scheduler used to assign Map and Reduce tasks in the Hadoop
> MR is the JobQueueTaskScheduler?

Yes, and it resides in the o.a.h.mapred.* package.

> 3 - How can I configure the Hadoop MR to use the FairScheduler? Is simply
> configuring the property mapred.jobtracker.taskScheduler?

Read: http://hadoop.apache.org/mapreduce/docs/r0.21.0/fair_scheduler.html#Configuration

-- 
Harsh J
www.harshj.com

Mime
View raw message