[Intel-gfx] frequent x crashes with gen6/sna

Daniel Vetter daniel at ffwll.ch
Mon Oct 17 13:58:03 CEST 2011


On Mon, Oct 17, 2011 at 01:45:28PM +0200, Dieter Mummenschanz wrote:
> Hi Daniel,
> 
> first of all I've seemed to screwed up my rc6 kernel parameters causing
> rc6 to be enabled in all my previous tests even though I thought it was
> disbaled. Sorry for that! Some new tests with i915_enable_rc6 definately
> being disabled didn't raise any gpu hangs no matter what I did! So rc6
> related clock changes might have something to do with the hangs/stalls.
> With rc6 being disabled, some opengl games, like prboom-plus however
> show random pixel depthbuffer errors. Is this a known issue?  Regarding
> the video streams causing the gpu hang, those are unfortunately
> copyrighted material (i.e. Star Wars Bluray for example). The best way
> is to play multiple hi bitrate-streams with different formats
> simultaneously and run a free OpenGL game like prboom-plus. I'll do some
> seaching on the web for free test streams to reproduce the hang. 

Oh, I don't want you to publish them, just check whether it's a specific
one or more random. And maybe it helps in reproducing.

> vainfo (latest git) shows:
> libva: libva version 0.32.0
> libva: va_getDriverName() returns 0
> libva: Trying to open /usr/local/lib/dri/i965_drv_video.so
> libva: va_openDriver() returns 0
> vainfo: VA API version: 0.32
> vainfo: Driver version: i965 Driver 0.1
> 
> the player is the latest mplayer hwaccel-vaapi branch (latest git)
> http://gitorious.org/vaapi/mplayer/commits/hwaccel-vaapi
> console command is mplayer -vo vaapi -va vaapi stream.mkv
> 
> Is there any way to monitor rc6 state change, i.e. gpu/ring clock speed?
> Maybe this helps to track down issues caused by rc6 state changes?

Ok, with have a new rc6 bug :( I think we'll attack the libva hang first,
I have an idea for a patch.

> Anyway sorry again for the rc6 confusion.
> 
> Regards,
> Dieter
-- 
Daniel Vetter
Mail: daniel at ffwll.ch
Mobile: +41 (0)79 365 57 48



More information about the Intel-gfx mailing list