You are viewing a plain text version of this content. The canonical link for it is here.

Posted to user@mahout.apache.org by Byung-Gon Chun <bg...@gmail.com> on 2010/04/14 19:50:13 UTC

workload with highly variable execution time

Hi,

I'm interested in looking at workload with highly variable mapper/reducer
execution time.
Which mahout workload do you recommend to run? I see clustering,
classification, recommendation, etc. Also, could you recommend what dataset
to use?

Thanks.
-Brian

Re: workload with highly variable execution time

Posted by Ted Dunning <te...@gmail.com>.

These are all very predictable, I think, since they are the sum of a lot of
small operations that don't vary much.

On Wed, Apr 14, 2010 at 2:16 PM, Byung-Gon Chun <bg...@gmail.com> wrote:

> > This may be too dumb but if your goal is to run a mapper/reducer that
> > takes a long time sometimes, just have then run a mapper that sleeps a
> > long time some times? a random number of milliseconds with wide range?
> >
> >
> Yes. But I'd like to find realistic workload. How about classification or
> clustering examples?

Re: workload with highly variable execution time

Posted by Byung-Gon Chun <bg...@gmail.com>.

Thanks, Sean.

On Wed, Apr 14, 2010 at 12:38 PM, Sean Owen <sr...@gmail.com> wrote:

> (I can tell you the recommender bits are pretty steady and
> predictable, so maybe not your best bet.)
>
> This may be too dumb but if your goal is to run a mapper/reducer that
> takes a long time sometimes, just have then run a mapper that sleeps a
> long time some times? a random number of milliseconds with wide range?
>
>
Yes. But I'd like to find realistic workload. How about classification or
clustering examples?

Thanks.
- Brian





> On Wed, Apr 14, 2010 at 6:50 PM, Byung-Gon Chun <bg...@gmail.com> wrote:
> > Hi,
> >
> > I'm interested in looking at workload with highly variable mapper/reducer
> > execution time.
> > Which mahout workload do you recommend to run? I see clustering,
> > classification, recommendation, etc. Also, could you recommend what
> dataset
> > to use?
> >
> > Thanks.
> > -Brian
> >
>

Re: workload with highly variable execution time

Posted by Sean Owen <sr...@gmail.com>.

(I can tell you the recommender bits are pretty steady and
predictable, so maybe not your best bet.)

This may be too dumb but if your goal is to run a mapper/reducer that
takes a long time sometimes, just have then run a mapper that sleeps a
long time some times? a random number of milliseconds with wide range?

On Wed, Apr 14, 2010 at 6:50 PM, Byung-Gon Chun <bg...@gmail.com> wrote:
> Hi,
>
> I'm interested in looking at workload with highly variable mapper/reducer
> execution time.
> Which mahout workload do you recommend to run? I see clustering,
> classification, recommendation, etc. Also, could you recommend what dataset
> to use?
>
> Thanks.
> -Brian
>