Re: Linux 6.10-rc2 - massive performance regression

[Johan Hovold]

On Sat, Jun 08, 2024 at 03:00:43PM -0700, Linus Torvalds wrote:
> On Sat, 8 Jun 2024 at 14:36, David Laight <David.Laight@xxxxxxxxxx> wrote:

> > I've done some tests.
> > I'm seeing a three-fold slow down on:
> > $ i=0; while [ $i -lt 1000000 ]; do i=$((i + 1)); done
> > which goes from 1 second to 3.
> >
> > I can run that with ftrace monitoring scheduler events (and a few
> > other things) and can't spot anywhere the process isn't running
> > for a significant time.
> 
> Sounds like cpu frequency. Almost certainly hw-specific. I went
> through that on my Threadripper in the 6.9 timeframe, but I'm not
> seeing any issues in this current release.
> 
> If you bisect it, we have somebody to blame and point fingers at...

This may possibly be related to the cpufreq/thermal regression I just
reported here:

	https://lore.kernel.org/lkml/ZmVfcEOxmjUHZTSX@xxxxxxxxxxxxxxxxxxxx/

which causes the big cores on the Lenovo ThinkPad X13s to be stuck at a
low frequency once they've been throttled.

Johan