On 6/25/2021 10:37 AM, Ionela Voinescu wrote: > Quick questions for you: > > 1. When you say you tried a 5.4 kernel, did you try it with these > patches backported? They also have some dependencies with the recent > changes in the arch topology driver and cpufreq so they would not be > straight forward to backport. No. It turned out that this 5.4-based kernel has "ondemand" governor by default which works fine which could even scale down to the lowest_perf (1000 MHz). Once switched the governor to "schedutil", it could keep the freq to the lowest. While on the latest kernel, it also works fine by using "ondemand" first and then switch to "schedutil". Even though it can only scale down to lowest_nonlinear_perf (2000 MHz). It is more of that using "schedutil" by default would not work. Also, on the latest kernel, even "userspace" governor only allows to scale down to 2000 MHz. > If the 5.4 kernel you tried did not have these patches, it might be best > to try next/master that has these patches, but with > CONFIG_ACPI_CPPC_CPUFREQ_FIE=n, just to eliminate the possibility that > an incorrect frequency scale factor here would affect utilization that > would then affect the schedutil frequency selection. I would not expect > this behavior even if the scale factor was wrong, but it would be good > to rule out. I'll try that at least see if CONFIG_ACPI_CPPC_CPUFREQ_FIE=n would make the latest kernel to be able to scale down to 1000 MHz. > 2. Is your platform booting with all CPUs? Are any hotplug operations > done in your scenario? Yes, booting with all CPUs. No additional hotplug there.
