Messages in this thread | | | Subject | Re: [patch 3/6] sched: use rq->avg_event to resurrect nohz ratelimiting | From | Mike Galbraith <> | Date | Fri, 18 Nov 2011 18:42:26 +0100 |
| |
On Fri, 2011-11-18 at 16:36 +0100, Peter Zijlstra wrote: > On Fri, 2011-11-18 at 16:19 +0100, Mike Galbraith wrote: > > Entering nohz at high frequency eats cycles, ratelimit it > > just as we do idle_balance(), and for the same reason. > > > > Signed-off-by: Mike Galbraith <efault@gmx.de> > > Arjan, can we do something smart with the idle governor which already > guestimates the idle duration for us?
That would be great. Won't help my Intel Q6600 though, the intel_idle governor doesn't support it. Other idle_governor gizmos really need to get smarter too.
-Mike
| |