Messages in this thread | | | Subject | Re: [PATCH 4/4] sched/fair: Use a recently used CPU as an idle candidate and the basis for SIS | From | Srinivas Pandruvada <> | Date | Wed, 31 Jan 2018 09:44:18 -0800 |
| |
On Wed, 2018-01-31 at 11:17 +0100, Peter Zijlstra wrote: > On Wed, Jan 31, 2018 at 10:22:49AM +0100, Rafael J. Wysocki wrote: > > On Tuesday, January 30, 2018 2:15:31 PM CET Peter Zijlstra wrote: > > > IA32_HWP_REQUEST has "Minimum_Performance", "Maximum_Performance" > > > and > > > "Desired_Performance" fields which can be used to give explicit > > > frequency hints. And we really _should_ be doing that. > > > > > > Because, esp. in this scenario; a task migrating; the hardware > > > really > > > can't do anything sensible, whereas the OS _knows_. > > > > But IA32_HWP_REQUEST is not a cheap MSR to write to. > > That just means we might need to throttle writing to it, like it > already > does for the regular pstate (PERF_CTRL) msr in any case (also, is > that a > cheap msr?) Much more throttling required compared to PERF_CTL. MSR_HWP_REQUEST is much slower compared to PERF_CTL (as high as 10:1).
> > Not touching it at all seems silly. > > But now that you made me look, intel_pstate_hwp_set() is horrible > crap. > You should _never_ do things like: > > rdmsr_on_cpu() > /* frob value */ > wrmsr_on_cpu() > > That's insane.
Since the cpufreq callback is not guaranteed to be called on the same CPU, we have to use rd/wrmsr_on_cpu(). But we can use smp_call_function_single() and optimize this. This function is called only during init, when usermode changes frequency limits and from thermal, so very few times.
Thanks, Srinivas
| |