[PATCH RFC 0/3] sched/fair: cpu time reserves for cgroups

Peter Zijlstra peterz at infradead.org
Mon May 16 12:26:45 UTC 2016

On Mon, May 16, 2016 at 03:22:22PM +0300, Konstantin Khlebnikov wrote:

> >You forgot to explain why I should care about this.
> As I told this works as low-limit or high-limit which allow to
> control cpu time distribution without hard limits and throttling.

That's what it does; I get that. However nothing tells me why I should
care about it. IOW, its a solution without a problem, and I tend to
ignore those -- saves a lot of time on my end.

> Present quota/hard limit has well known problems when it throttle task
> inside kernel where it holds mutexes. Also it's too strict and doesn't
> allow utilization of unused cpu time.

See; now you're starting to make sense. You cannot have a patch if you
don't have a problem. And this series didn't have a problem to solve.

As for the latter; that's a feature for many people I'm told.

More information about the Containers mailing list