ChanServ changed the topic of #lima to: Development channel for open source lima driver for ARM Mali4** GPUs - Kernel driver has landed in mainline, userspace driver is part of mesa - Logs at https://oftc.irclog.whitequark.org/lima/
camus has quit [Ping timeout: 480 seconds]
camus has joined #lima
camus1 has joined #lima
camus has quit [Read error: Connection reset by peer]
camus has joined #lima
camus1 has quit [Read error: Connection reset by peer]
megi has quit [Quit: WeeChat 3.4]
megi has joined #lima
camus1 has joined #lima
camus has quit [Ping timeout: 480 seconds]
camus has joined #lima
camus1 has quit [Read error: Connection reset by peer]
camus1 has joined #lima
camus has quit [Remote host closed the connection]
<hexdump0815>
with this tweak it was running fine and stable again
<hexdump0815>
ok - i was just able to trigger the problem again even with a limit of 1000
<enunes>
hexdump0815: yeah its a heuristic, in the MR we applied that if I recall correctly we did note that it was possible to craft some programs that would run into any arbitrary limit anyway
<hexdump0815>
enunes: so no real way around it?
<enunes>
i dont remember what was the condition to hit it
<anarsoul>
hexdump0815: fix it in vcvrack
<anarsoul>
hexdump0815: btw, can you share complete dmesg?
<anarsoul>
the two lines that you mention aren't relevant
<anarsoul>
I'm more interested to see what was the real error
<hexdump0815>
anarsoul: there was nothing more in dmesg - maybe i'll have to raise the debug level?
<enunes>
hexdump0815: really, fix that application :)
<anarsoul>
hexdump0815: try "dmesg | grep lima"
<hexdump0815>
fixing it in vcvrack is close to impossible due to its architecture and i think it is simply desgned with a different class of gpus in mind :) ... i'm happy that it runs at all on those little mali gpus
<hexdump0815>
maybe its also hw related - i have another s905x box which is a tiny bit faster with better mem bw and there it is running fine and stable with default values
<hexdump0815>
could also be that its gpu devfreq related as i saw some trouble related to this on that box as well (but not always related to the mentioned log msgs)
<hexdump0815>
i'll check further during the next days and in case i'll get any consistent report i'll let you know
<anarsoul>
hexdump0815: likely it hits task timeout
<anarsoul>
there's a kernel module parameter for lima, sched_timeout_ms
<anarsoul>
it's 500ms by default, you can increase it to 1s
<anarsoul>
or to 2s
<hexdump0815>
anarsoul: oh sorry - forgot to mention it - yes, it was running into the task timeout and i already had raised it to 1s which i remembered from an earlier debug session with you
<anarsoul>
looks like you need more than 1s
<anarsoul>
alternatively, you can run it with sw renderer :)