Messages in this thread | | | Date | Wed, 20 Mar 2019 13:25:14 +0100 | From | Peter Zijlstra <> | Subject | Re: [RFC][PATCH 6/8] perf/x86: Clear ->event_constraint[] on put |
| |
On Tue, Mar 19, 2019 at 02:50:21PM -0700, Stephane Eranian wrote: > On Thu, Mar 14, 2019 at 6:11 AM Peter Zijlstra <peterz@infradead.org> wrote: > > > > The current code unconditionally clears cpuc->event_constraint[i] > > before calling get_event_constraints(.idx=i). The only site that cares > > is intel_get_event_constraints() where the c1 load will always be > > NULL. > > > > However, always calling get_event_constraints() on all events is > > wastefull, most times it will return the exact same result. Therefore > > retain the logic in intel_get_event_constraints() and change the > > generic code to only clear the constraint on put. > > > > Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> > > I thought there was caching of the constraint in case it was static > (or unconstrained)
Yeah, I was under the same impression :-/
> to avoid walking the constraint table each time between invocations > on the same group_sched_in() call. But the way the c1 vs. c2 logic > is written I don't see it. In which case, this could be another opportunity.
Right, the next patch attempts this.
| |