Hi Chris,

On Sun, Nov 29, 2015 at 9:43 PM, Christopher Samuel
<[email protected]> wrote:
> We're looking at seeing if we can combine fair share with our existing
> quota system that uses GrpCPUMins.
>
> However, for fair share a decay factor is strongly suggested and I worry
> that there is an implication that the usage that GrpCPUMins compares
> against would decline and so allow a project to run jobs after having
> already hit their cap.
>
> Is that true?

I'd be very interested to know about this too. We (Stanford Research
Computing) have a use case where we need to make fairshare and
CPU.minutes hard limits co-exist on the same cluster for different
user communities.

Cheers,
-- 
Kilian

Reply via email to