<marex>
austriancoder: so tentatively, the BUG splat happens even when running just stress-ng and glmark, without the iperf3
<marex>
or the platform freezes and then WDT triggers reboot
<marex>
blargh
<lynxeye>
marex: Which platform? I've seen memory corruption due to insufficient SoC power supply on imx6qp under heavy GPU load.
JohnnyonF has joined #etnaviv
<marex>
lynxeye: MP1, still
JohnnyonFlame has quit [Ping timeout: 264 seconds]
<lynxeye>
marex: Okay, so not really related. But just keep in mind that this might be genuine DRAM corruption. In my case only a very specific Qt5 scene would trigger the issue, as only in this scene I could see brownouts on the SoC LDO. They were very short, but corrupted DRAM transactions, so the kernel would crash at random points way after the brownout happened.
<marex>
lynxeye: I already cranked the PMIC up two notches, so that shouldn't be the case here
pcercuei has quit [Read error: Connection reset by peer]
pcercuei has joined #etnaviv
gerddie3 has joined #etnaviv
gerddie has quit [Quit: Ping timeout (120 seconds)]
gerddie3 is now known as gerddie
t_unix[m] has quit [Ping timeout: 246 seconds]
lrusak has quit [Ping timeout: 268 seconds]
srk has quit [Remote host closed the connection]
srk has joined #etnaviv
t_unix[m] has joined #etnaviv
chewitt has quit [Quit: Zzz..]
lrusak has joined #etnaviv
kherbst has joined #etnaviv
karolherbst has quit [Ping timeout: 276 seconds]
lynxeye has quit [Quit: lynxeye]
karolherbst has joined #etnaviv
kherbst has quit [Ping timeout: 264 seconds]
kherbst has joined #etnaviv
karolherbst has quit [Ping timeout: 245 seconds]
kherbst is now known as karolherbst
karolherbst has quit [Quit: duh 🐧]
karolherbst has joined #etnaviv
kherbst has joined #etnaviv
karolherbst has quit [Ping timeout: 272 seconds]
kherbst is now known as karolherbst
mth has quit [Ping timeout: 260 seconds]
mth has joined #etnaviv
pdp7 has joined #etnaviv
berton has quit [Remote host closed the connection]