On Thu, Jul 16, 2020 at 3:14 AM Srinivas Pandruvada <srinivas.pandruvada@xxxxxxxxxxxxxxx> wrote: > > On Wed, 2020-07-15 at 14:35 -0700, Francisco Jerez wrote: > > "Rafael J. Wysocki" <rafael@xxxxxxxxxx> writes: > > > > > On Wed, Jul 15, 2020 at 2:09 AM Francisco Jerez < > > > currojerez@xxxxxxxxxx> wrote: > > > > "Rafael J. Wysocki" <rjw@xxxxxxxxxxxxx> writes: > > > > > > > > > From: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx> > > > > > > > [...] > > > > > > I don't think that's accurate. I've looked at hundreds of > > > > > traces > > while > > my series [1] was in control of HWP_REQ_MAX and I've never seen an > > excursion above the maximum HWP_REQ_MAX control specified by it > > within a > > given P-state domain, even while that maximum specified was well into > > the turbo range. So, yeah, I agree that HWP_REQ_MAX is nothing like > > a > > hard limit, particularly when multiple threads are running on the > > same > > clock domain, but the processor will still make its best effort to > > limit > > the clock frequency to the maximum of the requested maximums, even if > > it > > happens to be within the turbo range. That doesn't make it useless. > > The exact same thing can be said about controlling HWP_REQ_MIN as > > you're > > doing now in this revision of your patch, BTW. > > > > If you don't believe me here is the turbostat sample with maximum > > Bzy_MHz I get on the computer I'm sitting on right now while > > compiling a > > kernel on CPU0 if I set HWP_REQ_MAX to 0x1c (within the turbo range): > > > > > Core CPU Avg_MHz > > > Busy% Bzy_MHz HWP_REQ PkgWatt CorWatt > > > - - 757 27.03 2800 0x0000000000000000 7.1 > > > 3 4.90 > > > 0 0 2794 99.77 2800 0x0000000080001c04 7.1 > > > 3 4.90 > > > 0 2 83 2.98 2800 0x0000000080001c04 > > > 1 1 73 2.60 2800 0x0000000080001c04 > > > 1 3 78 2.79 2800 0x0000000080001c04 > > > > With the default HWP_REQUEST: > > > > > Core CPU Avg_MHz > > > Busy% Bzy_MHz HWP_REQ PkgWatt CorWatt > > > - - 814 27.00 3015 0x0000000000000000 8.4 > > > 9 6.18 > > > 0 0 2968 98.24 3021 0x0000000080001f04 8.4 > > > 9 6.18 > > > 0 2 84 2.81 2982 0x0000000080001f04 > > > 1 1 99 3.34 2961 0x0000000080001f04 > > > 1 3 105 3.60 2921 0x0000000080001f04 > > Correct. In HWP mode this is possible to lower limit in turbo region > conditionally. In legacy mode you can't with turbo activation ratio. > > But what we don't want set max and min perf and use like desired to run > at a P-state overriding HWP or limit the range where HWP can't do any > meaningful selection. That's a good point too IMO.
