On Wed, Nov 17, 2021 at 4:08 PM Lukasz Luba <lukasz.luba@xxxxxxx> wrote: > > > > On 11/17/21 12:49 PM, Rafael J. Wysocki wrote: > > On Wed, Nov 17, 2021 at 11:46 AM Lukasz Luba <lukasz.luba@xxxxxxx> wrote: > >> > >> Hi Rafael, > >> > >> On 11/16/21 7:05 PM, Rafael J. Wysocki wrote: > >>> On Mon, Nov 15, 2021 at 9:10 PM Thara Gopinath > >>> <thara.gopinath@xxxxxxxxxx> wrote: > >>>> > >>>> cpuinfo.max_freq can reflect boost frequency if enabled during boot. Since > >>>> we don't consider boost frequencies while calculating cpu capacities, use > >>>> policy->max to populate the freq_factor during boot up. > >>> > >>> I'm not sure about this. schedutil uses cpuinfo.max_freq as the max frequency. > >> > >> Agree it's tricky how we treat the boost frequencies and also combine > >> them with thermal pressure. > >> We probably would have consider these design bits: > >> 1. Should thermal pressure include boost frequency? > > > > Well, I guess so. > > > > Running at a boost frequency certainly increases thermal pressure. > > > >> 2. Should max capacity 1024 be a boost frequency so scheduler > >> would see it explicitly? > > > > That's what it is now if cpuinfo.max_freq is a boost frequency. > > > >> - if no, then schedutil could still request boost freq thanks to > >> map_util_perf() where we add 25% to the util and then > >> map_util_freq() would return a boost freq when util was > 1024 > >> > >> > >> I can see in schedutil only one place when cpuinfo.max_freq is used: > >> get_next_freq(). If the value stored in there is a boost, > >> then don't we get a higher freq value for the same util? > > > > Yes. we do, which basically is my point. > > > > The schedutil's response is proportional to cpuinfo.max_freq and that > > needs to be taken into account for the results to be consistent. > > > > This boost thing wasn't an issue for us, because we didn't have > platforms which come with it (till recently). I've checked that you have > quite a few CPUs which support huge boost freq, e.g. 5GHz vs. 3.6GHz > nominal max freq [1]. Am I reading this correctly as kernel boost freq? That actually depends on the driver. For instance, intel_pstate can be run with turbo (== boost) enabled or disabled. If turbo is enabled, cpuinfo.max_freq is the max turbo frequency. In acpi_cpufreq things are sort of weird, because the highest bin in there is a turbo frequency, but not the max one and it is used to enable the entire turbo range. The driver sets cpuinfo.max_freq to this one if boost is enabled IIRC. > Do you represent this 5GHz as 1024 capacity? Yes (but see above). > From this schedutil get_next_freq() I would guess yes. > > I cannot find if you use thermal pressure, could you help me with this, > please? It is not used on x86 AFAICS.
