On 09/05/19 13:48, Peter Zijlstra wrote: > On Thu, Sep 05, 2019 at 12:40:01PM +0100, Patrick Bellasi wrote: > > Right, although I think behaviours could still be exported but via a > > different and configurable interface, using thresholds. > > I would try _really_ hard to avoid pinning down behaviour. The more you > do that, the less you can change.
While I agree with that but I find there's a contradiction between not 'pinning down behavior' and 'easy and clear way to bias latency sensitive from end user's perspective'. Maybe we should protect this with a kconfig + experimental tag until trial and error show the best way forward? -- Qais Yousef
