alyssa changed the topic of #panfrost to: Panfrost - FLOSS Mali Midgard & Bifrost - Logs https://freenode.irclog.whitequark.org/panfrost - <daniels> avoiding X is a huge feature
stikonas has quit [Remote host closed the connection]
tlwoerner has joined #panfrost
raster has quit [Quit: Gettin' stinky!]
popolon has quit [Quit: WeeChat 2.9]
Net147 has quit [Quit: Quit]
Net147 has joined #panfrost
_whitelogger has joined #panfrost
icecream95 has joined #panfrost
<archetech> ok who removed blue from rgb in pfrost ? ;p
<HdkR> No need to feel so blue, we've removed it
<alyssa> for mental health
<HdkR> CMYK monitors instead
<alyssa> d'awwwww
<archetech> made my my kde wallpaper look pretty cool though
<SolidHal> clementp[m] or someone else that knows about dev-freq, I'm seeing cursor jumping at low gpu frequencies on xfce
<SolidHal> I'm on kernel 5.9.1, tested with and without https://patchwork.freedesktop.org/series/79442/
<icecream95> archetech: If you use a DRM driver with gamma ramp support, you could make everything blue instead
<archetech> ah so I have a choice of whats broke nice
<archetech> ty ill wait
<SolidHal> the cursor jumping goes away if I run "glxgears" or something else that stresses the gpu. I don't get any cursor jumping in gnome xorg/wayland.
<SolidHal> Thought it might be that when running "glxgears" the gpu frequency increased, so I hacked the operating points of the gpu so that it is always max freq/voltage, but that did not fix the issue, which is interesting
<SolidHal> read the current frequency with "/sys/devices/platform/ff9a0000.gpu/devfreq/ff9a0000.gpu/cur_freq" and "target_freq" and confirmed it is always at 80000000
<archetech> does glxinfo show opengl hw accell ?
<HdkR> `glxinfo | grep "OpenGL renderer"`
<SolidHal> direct rendering : yes
<SolidHal> OpenGL render string: Mali T860 (Panfrost)
bnieuwenhuizen has quit [Quit: No Ping reply in 180 seconds.]
<brads> SolidHal: have seen similar issues before with GPU accelleration enabled (libMali in this case), problem was with min cpu freq scaling rather than GPU. As CPU is not very utilised with GPU accel it was causing the mouse problems. Try to increase it with cpufreq util to see if it improves
bnieuwenhuizen has joined #panfrost
<SolidHal> brads I set all of the cores to max frequency, still the same issue
archetech has quit [Quit: Konversation terminated!]
<tomeu> SolidHal: it doesn't happen if you set the performance governor, right?
davidlt has joined #panfrost
archetech_n2 has joined #panfrost
archetech_n2 is now known as archetech
_whitelogger has joined #panfrost
_4of7 has quit [Ping timeout: 265 seconds]
archetech has quit [Quit: Leaving]
_4of7 has joined #panfrost
archetech has joined #panfrost
archetech has quit [Quit: Leaving]
davidlt has quit [Ping timeout: 240 seconds]
archetech has joined #panfrost
raster has joined #panfrost
steev has quit [Ping timeout: 272 seconds]
daniels has quit [Ping timeout: 272 seconds]
daniels has joined #panfrost
steev has joined #panfrost
kaspter has joined #panfrost
Elpaulo has joined #panfrost
alpernebbi has joined #panfrost
warpme_ has quit [Quit: Connection closed for inactivity]
robmur01_ has joined #panfrost
robmur01 has quit [Ping timeout: 256 seconds]
stikonas has joined #panfrost
archetech has quit [Quit: Leaving]
kaspter has quit [Ping timeout: 260 seconds]
icecream95 has quit [Quit: leaving]
ente has joined #panfrost
archetech has joined #panfrost
davidlt has joined #panfrost
jernej has quit [Quit: Free ZNC ~ Powered by LunarBNC: https://LunarBNC.net]
jernej has joined #panfrost
jernej has quit [Quit: Free ZNC ~ Powered by LunarBNC: https://LunarBNC.net]
robmur01_ is now known as robmur01
davidlt has quit [Ping timeout: 265 seconds]
jernej has joined #panfrost
dstzd has quit [Quit: ZNC - https://znc.in]
dstzd has joined #panfrost
dstzd has quit [Client Quit]
jernej has quit [Quit: Free ZNC ~ Powered by LunarBNC: https://LunarBNC.net]
jernej has joined #panfrost
dstzd has joined #panfrost
jernej has quit [Client Quit]
jernej has joined #panfrost
dstzd has quit [Client Quit]
jernej has quit [Client Quit]
jernej has joined #panfrost
jernej has quit [Client Quit]
jernej has joined #panfrost
dstzd has joined #panfrost
stikonas has quit [Remote host closed the connection]
vstehle has joined #panfrost
indy has quit [Read error: Connection reset by peer]
indy has joined #panfrost
stikonas has joined #panfrost
TheMojoMan has joined #panfrost
TheMojoMan has quit [Client Quit]
davidlt has joined #panfrost
popolon has joined #panfrost
<SolidHal> tomeu I have the governor set to performance on the cpu. The gpu doesn't support a performance governor. The only way I can consistently stop the cursor jumping is by running glxgears, glxheads, likely other graphic intensive programs
gcl_ has joined #panfrost
<macc24> SolidHal: is SWCursor set to true in xorg config?
gcl has quit [Ping timeout: 256 seconds]
gcl has joined #panfrost
gcl_ has quit [Ping timeout: 265 seconds]
TheMojoMan has joined #panfrost
TheMojoMan has quit [Quit: Connection closed]
warpme_ has joined #panfrost
gcl_ has joined #panfrost
<SolidHal> macc24 I set "SWCursor" to "off" and "HWCursor" to "on" in my libinput xorg.conf, no change, but I'm not sure how to validate the setting stuck. I tried to generate the config with "sudo Xorg :2 -configure" and got an interesting error: "No devices to configure. Configuration failed.". And nothing mesa/panfrost related shows up under the "List of
<SolidHal> video drivers" Xorg -configure prints out
gcl has quit [Ping timeout: 260 seconds]
gcl has joined #panfrost
raster has quit [Quit: Gettin' stinky!]
gcl_ has quit [Ping timeout: 240 seconds]
<macc24> oh god
<macc24> Xorg -configure is deprecated iirc
<alyssa> > Xorg is deprecated
<alyssa> FTFY
<SolidHal> hmm, it seems it slightly happens on gnome wayland, and a bit more on gnome xorg. I have the FPS monitor mesa debug up, and it displays only on gnome xorg and wayland, but not on xfce. Something I noticed is that the fps spikes to around 60fps for a while after just logging in to gnome, but drops within a minute to ~1-8fps and I see the cursor
<SolidHal> jump.
raster has joined #panfrost
<SolidHal> this behavior is the same with and without the devfreq patches https://patchwork.freedesktop.org/series/79442/
nlhowell has quit [Quit: WeeChat 2.9]
<SolidHal> ah, found the most obvious signal to look for while debugging this. in /var/log/Xorg.0.log I see lots of "Atmel maXTouch Touchpad: client bug: eventprocessing lagging behind by 101ms, your system is too slow"
<SolidHal> aaaand I see the same Atmel event processing lagging complaints in wayland as gnome-shell libinput errors
gcl_ has joined #panfrost
gcl has quit [Ping timeout: 240 seconds]
Green has quit [Quit: ...]
Green has joined #panfrost
<alyssa> SolidHal: eh?
ckeepax has quit [Ping timeout: 272 seconds]
<SolidHal> alyssa just the cursor jumping issue I'm debugging
<archetech> kernel driver id say
nlhowell has joined #panfrost
warpme_ has quit [Quit: Connection closed for inactivity]
archetech has quit [Quit: Leaving]
davidlt has quit [Ping timeout: 240 seconds]
alpernebbi has quit [Quit: alpernebbi]
ente has quit [Remote host closed the connection]
ente has joined #panfrost
raster has quit [Quit: Gettin' stinky!]
stikonas has quit [Remote host closed the connection]