kernel 2.6.9-rc2-mm2 vs glxgears

Felix Kühling fxkuehl at gmx.de
Wed Sep 29 03:21:57 PDT 2004


On Tue, 28 Sep 2004 23:56:15 -0400
Gene Heskett <gene.heskett at verizon.net> wrote:

> On Tuesday 28 September 2004 18:21, Felix Kühling wrote:
> >On Tue, 28 Sep 2004 15:34:36 -0400
[snip]
> >
> >Sounds like it could be a problem with frame throttling. My guess is
> >that interrupts get delayed somehow. The driver uses them to wait
> > for previous frames to finish rendering. You can try different
> > settings that don't use interrupts using the environment variable
> > fthrottle_mode, e.g.
> >
> >fthrottle_mode=0 glxgears (busy waiting)
> >fthrottle_mode=1 glxgears (usleeps)
> >fthrottle_mode=2 glxgears (interrupts, the default)
> 
> Humm, interesting results:

Indeed. Frame throttling is obviously not the problem. Low CPU usage
even with busy waiting indicates that the driver gives away the CPU when
it shouldn't. There was a discussion about proper use of sched_yield and
2.6 kernels some time ago. Was this issue resolved?

> [root at coyote linux-2.6.9-rc2]# fthrottle_mode=0 glxgears
> ATTENTION: default value of option fthrottle_mode overridden by 
> environment.
> IRQ's not enabled, falling back to busy waits: 11 0 5
> 826 frames in 5.0 seconds = 165.200 FPS
> 992 frames in 5.0 seconds = 198.400 FPS
> 991 frames in 5.0 seconds = 198.200 FPS
> 821 frames in 5.0 seconds = 164.200 FPS
[snip]

What are you doing differently when you get 10fps? (Different kernel?)
What effect does fthrottle_mode have in that configuration?


| Felix Kühling <fxkuehl at gmx.de>                     http://fxk.de.vu |
| PGP Fingerprint: 6A3C 9566 5B30 DDED 73C3  B152 151C 5CC1 D888 E595 |



More information about the xorg mailing list