[Intel-gfx] gpu freeze
pcjc2 at cam.ac.uk
Sat Oct 30 12:09:57 PDT 2010
On Sat, 2010-10-30 at 20:22 +0200, Alexey Fisher wrote:
> What info should i collect if i get GPU hung?
> I currently get one, with kernel 2.6.36-07532-gbbe2e11
> it happened after i started video. Interesting is my PC worked 15 hours,
> many things was done it was not first video. So fear i can't reproduce
> or bisect it. This is first hung for some weeks or months...
As a non-expert, non-canonical answer (in the non-commercial sense of
the word canonical), I would primarily be interested in saving the
contents of /sys/kernel/debug/dri/0/i915_error_state
You can decompile that with "intel_error_decode $file"
Also, note if there are any interesting messages in dmesg pertaining to
drm / gem / i915 (caps or non-caps for all), and anything unusual in the
end of /var/log/Xorg.0.log or /var/log/Xorg.0.log.old if your X server
The error state ought to be relevant to the hang assuming you've not
rebooted or had any subsequent hangs.
Electrical Engineering Division,
University of Cambridge,
9, JJ Thomson Avenue,
Tel: +44 (0)7729 980173 - (No signal in the lab!)
Tel: +44 (0)1223 748328 - (Shared lab phone, ask for me)
More information about the Intel-gfx