[ltp] Temperature increase after S2Ram
Mon, 08 Jul 2013 09:48:59 +0200
On Mon, 2013-07-08 at 00:07 -0300, Henrique de Moraes Holschuh wrote:
> On Sun, 07 Jul 2013, Paul Bolle wrote:
> > Somehow it seems powertop triggers Heisenbug behavior! If the second
> > core is apparently stuck at 2 GHz, and I start powertop to see what's
> > going on, the second core will again drop down to 800 MHz, eventually.
> > But quitting powertop makes the second core jump to 2 GHz again (judging
> > by /proc/cpuinfo's output, that is).
> > That is strange! So let's assume for now that I see patterns that just
> > aren't there. Ie, this needs more testing on my side.
> Nah, let's assume 3.10 is borked. Please check whether the latest 3.9.x
> works well for you...
I hope to do so shortly.
> > > and turbostat
> > $ sudo ./turbostat -S
> > No invariant TSC
> I see. Can powertop show idle states on that box? If it does, keep an eye
> on them.
But powertop (at least) masks the problem: while powertop is running
CPU1 (the second core that seems to be stuck at going 2 GHz) does drop
back to 800 MHz.
Another curious thing, perhaps related: acpi_cpufreq's refcount wraps
after offlining and onlining this core a few times:
$ cat /proc/modules | grep acpi_cpufreq
acpi_cpufreq 19612 18446744073709551609 - Live 0xffffffffa0465000 (F)
mperf 12607 1 acpi_cpufreq, Live 0xffffffffa0418000 (F)
18446744073709551609 equals (2 ^ 64) - 7. I guess I've offlined that
core seven times now.