Re: [Condor-users] Problems with jobs

[Matt Hope <matthew.hope@xxxxxxxxx>]

Great glad to help. if you ever feel like optimizing it to find the
optimal ratio of job length as a function of the number of machines
and the amount of io per job, I (and quite prob many other people on
the list) would love to know.

good luck with your pool
Matt

On 12/9/05, Chris Miles <chrismiles@xxxxxxxxxxxxxxxx> wrote:
> Everything is so much better now.
>
> My main executable is just a simple script file which runs my app 100 times.
> So altogether I submitting 100 jobs each running 100 jobs on each machine.
>
> Every machine fired into action.
>
> 10,000 jobs completed in 4 minutes -- so you can see the kind of speed the
> jobs run and how fast the cluster machines are haha.
>
> Many Thanks for your help
>
> Chris
>
> ----- Original Message -----
> From: "Matt Hope" <matthew.hope@xxxxxxxxx>
> To: "Chris Miles" <chrismiles@xxxxxxxxxxxxxxxx>
> Cc: "Condor-Users Mail List" <condor-users@xxxxxxxxxxx>
> Sent: Friday, December 09, 2005 8:33 AM
> Subject: Re: [Condor-users] Problems with jobs
>
> Not if the overhead of negotiation / data transfer (both of which
> would not occur if you ran locally) is sizable compared to the length
> of the job
>
> > Might it be possible to have my condor job do more than 1 of my jobs?
>
> absolutely - this is a much better idea
>
>
>
>