Possible Performance Regression with Mesa

Lucas Stach l.stach at pengutronix.de
Thu Apr 25 08:58:33 UTC 2024


Hi Joao Paulo,

Am Mittwoch, dem 24.04.2024 um 19:31 -0300 schrieb Joao Paulo Silva
Goncalves:
> Hello all,
> 
> We might have encountered a performance regression after upgrading from Mesa
> 2022.0.3 to 2024.0.2. During our automated hardware tests using LAVA, we noticed
> a lower score on glmark2 when we upgraded from the OpenEmbedded release from
> Kirkstone to Scartgarth. After conducting some internal tests, it doesn't seem
> to be an issue with the kernel or the glmark2 tool version, so we suspect that
> the issue may be related to something within Mesa. We believe that there might
> be something we're overlooking. Do you have any ideas or insights about
> this problem?
> 
Etnaviv added some resource tracking to fix issues with a number of
use-cases, which did add some CPU overhead and might cost some
performance, but should no be as dramatic as the numbers you are seeing
here.

> Here are some details about our hardware platform and some tests we
> have conducted:
> 
> Platform: Toradex Apalis iMX6 - NXP i.MX 6Q/6D Arm Cortex A9 with
> Vivante GC2000 rev 5108 using Etnaviv.
> 
> Tests:
> 
> Kernel Versions - v6.1.87 and v6.9-rc4
> Glmark2 Versions - 2021.12 and 2023.01
> 
> We combined different upstream kernel, Mesa, and glmark2 versions and
> ran glmark2 on each
> combination on a mostly idle system. The benchmark was run 20 times on
> each combination.
> 
> Some Results:
> 
> > Kernel   |   Mesa    | glmark2 | Max-Min Score
> v6.1.87     2022.0.3    2021.12   449-495
> v6.9-rc4    2022.0.3    2021.12   452-502
> v6.1.87     2022.0.3    2023.01   453-504
> v6.9-rc4    2022.0.3    2023.01   455-496
> v6.1.87     2024.0.2    2021.12   301-313
> v6.9-rc4    2024.0.2    2021.12   298-320
> v6.1.87     2024.0.2    2023.01   301-313
> v6.9-rc4    2024.0.2    2023.01   295-310

Since the glmark2 cumulative score can be skewed quite heavily by
single tests, it would be interesting to compare the results from
individual benchmark tests. Do you see any outliers there or is the
performance drop across the board?

Regards,
Lucas


More information about the mesa-dev mailing list