Re: Odd performance problems with Lenovo L15

On Mon, Jan 10, 2022 at 9:46 AM Eugene Grosbein <eugen@grosbein.net> wrote:

> 10.01.2022 12:12, Kevin Oberman wrote:
>
> > I continue to see odd performance issues and just noticed something I
> can put my finger on that may explain it. It has gone from odd to totally
> off the rails. Any ideas will be appreciated.
> >
> > Normally, on an idle system I see all CPUs running at full speed.
> > dev.cpu.7.freq: 2101
> > dev.cpu.6.freq: 2101
> > dev.cpu.5.freq: 2101
> > dev.cpu.4.freq: 2101
> > dev.cpu.3.freq: 2101
> > dev.cpu.2.freq: 2101
> > dev.cpu.1.freq: 2101
> > dev.cpu.0.freq: 2101
> >
> > But, during a large compile (e.g. llvm or firefox), things sometimes go
> wonky. Everything slows to a crawl. And, I see:
> > dev.cpu.7.freq: 400
> > dev.cpu.6.freq: 400
> > dev.cpu.5.freq: 400
> > dev.cpu.4.freq: 400
> > dev.cpu.3.freq: 400
> > dev.cpu.2.freq: 400
> > dev.cpu.1.freq: 400
> > dev.cpu.0.freq: 2101
>
> Did you set by any chance sysctl hw.acpi.thermal.tz0.passive_cooling=1 ?
> Maybe, some other non-default settings for any of hw.acpi.thermal.* in
> /etc/sysctl.conf or /boot/loader.conf?
> Is powerd(8) started?
>
> Also, you did not mention your FreeBSD version


Sorry for the long delay in responding.

No changes from the default hw.acpi.thermal settings.
FreeBSD ptavv 13.0-STABLE FreeBSD 13.0-STABLE #1
stable/13-n248149-87c8d285397: Sat Nov 20 17:00:28 PST 2021
root@ptavv:/usr/obj/usr/src/amd64.amd64/sys/GENERIC.4BSD
 amd64

I have been seeing strange performance problems for some time; probably
since about when 13.0 was released, maybe since I started using the system
after it was discovered that disabling P-States stopped the system freezes
I had been experiencing.

This is not regularly reproducible. I built llvm90 and then did a
buildworld yesterday without the issue showing up.

Normally a large build will show temperatures rise and fall between about
45C and 92C. The fan will speed up as the temperature rises and slow when
it falls. This happens over a period of minutes and never seems to find a
"medium" point where the temperature stabilizes. When the problem shows up,
the temperature drops to near idle levels and the build takes a very long
time.

I have not tried forcing the frequency back to the 2.1G max speed.

I'm probably still missing some behaviors, but I think this is most of it.

Thanks for the response. Sorry again for the long delay in respoinding.
-- 
Kevin Oberman, Part time kid herder and retired Network Engineer
E-mail: rkoberman@gmail.com
PGP Fingerprint: D03FB98AFA78E3B78C1694B318AB39EF1B055683