Re: Fair Scheduler pools regardless of users

[Patai Sangbutsarakum <si...@gmail.com>]

'-Dmapred.fairscheduler.pool=pool_name' will just shoot to the specified
pool.

/server/hadoop/bin/hadoop jar hadoop-examples-0.20.2-cdh3u0.jar wordcount
-Dmapred.fairscheduler.pool=pool_name input output


On Mon, Jul 8, 2013 at 3:11 PM, Sandy Ryza <sa...@cloudera.com> wrote:

> Hi Amit,
>
> You can set the mapred.job.queue.name to the name of the queue you want
> to submit it to.  If the queue does not exist, it will be created.  If you
> want to configure a queue with particular properties, you can do so in the
> Fair Scheduler allocations file.  See
> http://hadoop.apache.org/docs/stable/fair_scheduler.html.
>
> -Sandy
>
>
> On Mon, Jul 8, 2013 at 3:53 AM, Amit Sela <am...@infolinks.com> wrote:
>
>> Hi all,
>>
>> I was wondering if there is a way to let fair scheduler ignore the user
>> and submit a job to a specific pool.
>> I would like to have 3/4 pools:
>>
>> 1. Very short (~1 min) routine jobs.
>> 2. Normal processing time (<1 hr) routine jobs.
>> 3. Long (days) experimental jobs.
>> 4. ? ad hoc immediate jobs ?
>>
>> Users matter less in my use case.
>>
>> Thanks,
>>
>> Amit.
>>
>> (Running 20 nodes cluster with Hadoop 1.0.4)
>>
>>
>>
>
>