sorear changed the topic of #riscv to: RISC-V instruction set architecture | https://riscv.org | Logs: https://libera.irclog.whitequark.org/riscv | Matrix: #riscv:catircservices.org
damian101 has quit [Ping timeout: 246 seconds]
vagrantc has quit [Quit: leaving]
zBeeble has quit [Read error: Connection reset by peer]
zBeeble has joined #riscv
hwspeedy has quit [Read error: Connection reset by peer]
Tenkawa has quit [Quit: Was I really ever here?]
test924 has joined #riscv
BootLayer has joined #riscv
X-Scale has quit [Quit: Client closed]
atka has quit [Ping timeout: 265 seconds]
hexdump0815 has quit [Ping timeout: 248 seconds]
hexdump0815 has joined #riscv
Armand|T420 has quit [Ping timeout: 265 seconds]
levitating has quit [Remote host closed the connection]
atka has joined #riscv
JanC has quit [Ping timeout: 265 seconds]
JanC has joined #riscv
Starfoxxes has quit [Ping timeout: 244 seconds]
jacklsw has joined #riscv
JanC is now known as Guest1029
Guest1029 has quit [Killed (silver.libera.chat (Nickname regained by services))]
JanC has joined #riscv
JanC_ has joined #riscv
JanC has quit [Killed (erbium.libera.chat (Nickname regained by services))]
JanC_ is now known as JanC
jobol has joined #riscv
JanC_ has joined #riscv
JanC has quit [Ping timeout: 260 seconds]
JanC has joined #riscv
JanC_ has quit [Ping timeout: 265 seconds]
heat has quit [Ping timeout: 248 seconds]
BootLayer has quit [Quit: Leaving]
damian101 has joined #riscv
JanC has quit [Ping timeout: 252 seconds]
JanC has joined #riscv
TMM has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
TMM has joined #riscv
mlw has joined #riscv
indy has quit [Ping timeout: 276 seconds]
JanC_ has joined #riscv
JanC is now known as Guest7191
Guest7191 has quit [Killed (molybdenum.libera.chat (Nickname regained by services))]
JanC_ is now known as JanC
seasharp has joined #riscv
seasharp_ has quit [Ping timeout: 245 seconds]
danilogondolfo has quit [Read error: Connection reset by peer]
danilogondolfo has joined #riscv
davidlt_ has joined #riscv
JanC_ has joined #riscv
JanC has quit [Killed (tantalum.libera.chat (Nickname regained by services))]
JanC_ is now known as JanC
ldevulder has joined #riscv
JanC_ has joined #riscv
JanC is now known as Guest9364
JanC_ is now known as JanC
naoki has quit [Quit: naoki]
Guest9364 has quit [Ping timeout: 252 seconds]
levitating has joined #riscv
levitating has quit [Remote host closed the connection]
levitating has joined #riscv
levitating_ has joined #riscv
JanC_ has joined #riscv
JanC has quit [Ping timeout: 252 seconds]
JanC_ is now known as JanC
levitating has quit [Ping timeout: 265 seconds]
atka has quit [Ping timeout: 265 seconds]
atka has joined #riscv
JanC has quit [Ping timeout: 272 seconds]
JanC has joined #riscv
jimbzy has quit [Quit: ZNC 1.8.2+deb2build5 - https://znc.in]
JanC_ has joined #riscv
JanC is now known as Guest781
Guest781 has quit [Killed (calcium.libera.chat (Nickname regained by services))]
JanC_ is now known as JanC
JanC_ has joined #riscv
JanC has quit [Killed (tantalum.libera.chat (Nickname regained by services))]
JanC_ is now known as JanC
levitating has joined #riscv
levitating_ has quit [Ping timeout: 272 seconds]
alperak has joined #riscv
jjido has joined #riscv
davidlt has joined #riscv
mlw has quit [Read error: Connection reset by peer]
mlw has joined #riscv
jjido has quit [Quit: My laptop has gone to sleep. ZZZzzz…]
ncopa has quit [Changing host]
ncopa has joined #riscv
X-Scale has joined #riscv
Stat_headcrabbed has joined #riscv
coldfeet has joined #riscv
jacklsw has quit [Quit: Back to the real world]
Stat_headcrabbed has quit [Quit: Stat_headcrabbed]
Stat_headcrabbed has joined #riscv
coldfeet has quit [Remote host closed the connection]
davidlt_ has quit [Ping timeout: 244 seconds]
davidlt has quit [Ping timeout: 252 seconds]
davidlt_ has joined #riscv
davidlt has joined #riscv
heat has joined #riscv
naoki has joined #riscv
somlo_ is now known as somlo
naoki has quit [Quit: naoki]
X-Scale has quit [Quit: Client closed]
zBeeble has quit [Ping timeout: 272 seconds]
zBeeble has joined #riscv
Tenkawa has joined #riscv
levitating has quit [Remote host closed the connection]
X-Scale has joined #riscv
psydroid has joined #riscv
___nick___ has joined #riscv
levitating has joined #riscv
hwspeedy has joined #riscv
andyc has joined #riscv
X-Scale has quit [Ping timeout: 256 seconds]
zBeeble42 has joined #riscv
zBeeble has quit [Read error: Connection reset by peer]
levitating has quit [Remote host closed the connection]
BootLayer has joined #riscv
coldfeet has joined #riscv
<mps> Tenkawa: do you still have high load on bananapi f3?
<Tenkawa> mps: haven't worked on it in a few days... depends on how I set it up
<mps> which scheduler you use
<Tenkawa> tried all of them
<Tenkawa> are you using a nvme root?
<Tenkawa> until you do your testing is irrelevant
<mps> well, I found high load is with schedutil, changing to performance or conservative load is 0.00
<Tenkawa> This happens on all schedulers with nvme drives
<mps> did you tested
<Tenkawa> yes
<mps> aha, ok
<Tenkawa> I "started" with performace
<Tenkawa> er performance
<ncopa> i observed the high cpu load today
<ncopa> with the bananapi bpi-f3
<ncopa> i run docker with data storage on nvme
<ncopa> use it as a gitlab runner
<Tenkawa> yep. We found the
<davidlt_> We noticed that high loads on idle exist, and that comes from mailbox driver.
<Tenkawa> davidlt_: its mailbox + remoteproc
<davidlt_> If you disable mailbox loads go down, yet to no longer can go "turbo mode" to 1.8GHz on M1.
<Tenkawa> but fixing it makes the unit unstable
<davidlt_> Someone on Fedora/RISCV Matrix channel has a workaround/patch, but is waiting to get account to gitee.com
<ncopa> is this reported upstream?
<Tenkawa> I can consistently lock it up in about 15 seconds now
<ncopa> i tried to create account on gitee.com but got 500
<Tenkawa> ncopa: they are on holiday for aother week
<Tenkawa> If you mean Bianbu
<Tenkawa> We really need to find resources to try to upstream it....
<davidlt_> The patch posted on Fedora/RISCV matrix channel is this: https://paste.centos.org/view/e451612d
<mps> davidlt_: alpine kernel have disabled these options
<davidlt_> Yeah, but we noticed you cannot get to 1.8GHz if you do this. IIRC mailbox/remoteproc is needed to talk to PM bits (co-processor?).
<Tenkawa> Disabling them works but it still will lockup nvme
<Tenkawa> davidlt_: exactly
<Tenkawa> there's something badly io routed too....
<davidlt_> We have 4 (or more) boards connected in Fedora/RISCV Koji farm. I don't think we ever saw NVMe lockups or similar.
<mps> Tenkawa: ncopa use kernel on nvme with these disabled
<Tenkawa> mps: and he just stated he sees the same high load
<Tenkawa> [11:19:42] ncopa: i observed the high cpu load today
<mps> Tenkawa: yes, but when changing scheduler load on his machine goes down
<ncopa> PID PPID USER STAT VSZ %VSZ CPU %CPU COMMAND
<ncopa> 117 2 root RW 0 0% 6 12% [sugov:0]
<mps> he can confirm
<ncopa> was a process named [sugov:0] that too 100% of one cpu
<ncopa> google told me it is related the cpu scheduler
<mps> right, I found this last night
<ncopa> when switching to "performance" CPU scheduler it went down
<ncopa> but i dont know yet if it will re-appear
<jn> "SUGOV stands for SchedUtil GOVernor.", TIL
<Tenkawa> Thats a governor thread... if you
<Tenkawa> er if you don't have the right scheduling options set it can spin
<Tenkawa> there's dt options that also go with the scheduler subsystem
<Tenkawa> not just "which" scheduler
<davidlt_> I assume it went away because you asked for "performance", and thus probably doesn't need to talk to PM that much.
<mps> jn: thanks, I wondered what is this strange name
<mps> davidlt_: also conservative works fine
<davidlt_> Yeah, anyways it's a bug in vendor kernel.
<Tenkawa> davidlt_: Yeah I am curious about PM too... I turn it all off
ldevulder has quit [Quit: Leaving]
<Tenkawa> davidlt_: indeed... many...
<mps> wonder why they touch schedutil at all
<davidlt_> Yeah, Jason files 10+ issues while trying to compile their kernel for Fedora.
<Tenkawa> I thought Rockchip on Arm and Starfive chips were "fun" lol
<ncopa> i had a discussion earlier with mps re cpu scheduler. it was me who changed it to schedutil for alpine, and mps claimed it is bad.
<ncopa> turns out mps was right
<ncopa> i bumped the kernel to 6.6.53 also
vagrantc has joined #riscv
<davidlt_> Well, wait 1-2 years and we might be able to boot upstream :)
<Tenkawa> Yeah mine is on lol
<Tenkawa> er lol
<mps> to add to ncopa message, our (alpine) kernel boot fine on lpi3a also
davidlt_ has quit [Quit: Leaving]
<ncopa> in case someone wants compare how the conflicts with bianbu kernel was solved
<mps> also we have ready-made images for sd card
<mps> and ncopa have better one but I forgot where
<ncopa> i need to recreate it with latest kernel
<mps> ncopa: maybe wait a little till I push opensbi and u-boot to aports
<mps> then we will complete alpine solution for bpif3 and lpi3a
jmontleon has joined #riscv
ZipCPU has quit [Quit: ZNC 1.7.5+deb4 - https://znc.in]
billchenchina- has joined #riscv
ZipCPU has joined #riscv
hwspeedy has quit [Read error: Connection reset by peer]
levitating has joined #riscv
psydroid has quit [Quit: KVIrc 5.0.0 Aria http://www.kvirc.net/]
psydroid has joined #riscv
davidlt has quit [Ping timeout: 265 seconds]
jobol has quit [Quit: Leaving]
davidlt has joined #riscv
___nick___ has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
___nick___ has joined #riscv
___nick___ has quit [Client Quit]
___nick___ has joined #riscv
billchenchina- has quit [Remote host closed the connection]
<mps> davidlt: for remoteproc to work binary firmware is needed, named esos.elf, and I can't find source for it. looks like it is small real time OS
<Tenkawa> yep
<mps> remoteproc is riscv32 and that is all I know about it
<Tenkawa> Yeah not very useful in most envs
<mps> this 300MHz will be nice to have but for me board is useful without it. don't like to use unknown binaries on my machines
bsFFFFFF has joined #riscv
<Tenkawa> (... or semi/non-functional)
bsFFFFFF has quit [Ping timeout: 245 seconds]
Noisytoot has quit [Quit: ZNC 1.9.1 - https://znc.in]
bsFFFFFF has joined #riscv
<mps> though I have again strange finding, with the latest alpine linux-spacemit kernel even with schedutil governor on idle system load is 0.00
<mps> I hope ncopa will test it on board with nvme and tell us
<mps> or it could be because I use new opensbi and u-boot
Noisytoot has joined #riscv
<Tenkawa> mps: what kernel version?
<mps> mainline 6.6.53 with bianbu patches
coldfeet has quit [Remote host closed the connection]
<Tenkawa> Nod wanted to make sure you were using 6.6
X-Scale has joined #riscv
<Tenkawa> 6.1 apparently doesn't have this problem
<Tenkawa> (I didn't test 6.1 more than a few hours so I can't confirm)
<mps> I didn't used 6.1 much, just to get 6.6 booting
<Tenkawa> I wish there was an actual spi nor chip on my unit so I could just boot straight to the nvme and figure this io path out in its most simple number of variables
<mps> that would be nice to have
davidlt has quit [Ping timeout: 260 seconds]
Noisytoot has quit [Ping timeout: 246 seconds]
<Tenkawa> mps: yeah... just having an empty socket and no chip is just... mean
<mps> Tenkawa: it doesn't work also for me though I think it is on board, spi-nor spi4.0: unrecognized JEDEC id bytes: 00 00 00 00 00 00
<Tenkawa> Are you sure there's one soldered on?
<mps> not sure
<Tenkawa> Noone I know has had one yet
<Tenkawa> only the 2gb ram ones have
<Tenkawa> and those are rare
<mps> my board is 2GB RAM
levitating has quit [Remote host closed the connection]
levitating has joined #riscv
<jmontleon> I see the same on BPI `spi-nor spi4.0: unrecognized JEDEC id bytes: 00 00 00 00 00 00`. Jupiter shows `spi-nor spi4.0: gd25q64 (8192 Kbytes)`. I did not have luck getting that to boot off nvme either although I did not try super hard. Powering it on the board looked basically dead until I added an sd card.
levitating_ has joined #riscv
<Tenkawa> jmontleon: you have to chainload it from microsd
levitating has quit [Ping timeout: 252 seconds]
<mps> hm, looks like load if 1.00 is when using schedutil governor and boot from emmc. boot and using from sd card load with schedutil is 0.00
<mps> s/load if/load of/
<Tenkawa> That would make sense... different io path
<Tenkawa> I haven't used the emmc for anything... too easy to crash it and be a pain to fix
mlw has quit [Ping timeout: 265 seconds]
jedesa has quit [Remote host closed the connection]
yaneti has joined #riscv
davidlt has joined #riscv
jedesa has joined #riscv
BootLayer has quit [Quit: Leaving]
frkazoid333 has quit [Ping timeout: 252 seconds]
frkazoid333 has joined #riscv
frkazoid333 has quit [Remote host closed the connection]
frkazoid333 has joined #riscv
frkazoid333 has quit [Remote host closed the connection]
TMM has quit [Quit: https://quassel-irc.org - Chat comfortably. Anywhere.]
TMM has joined #riscv
andyc has quit [Quit: Connection closed for inactivity]
levitating_ has quit [Ping timeout: 252 seconds]
levitating_ has joined #riscv
mlw has joined #riscv
jjido has joined #riscv
hwspeedy has joined #riscv
zBeeble42 has quit [Ping timeout: 248 seconds]
jjido has quit [Quit: My laptop has gone to sleep. ZZZzzz…]
davidlt has quit [Ping timeout: 276 seconds]
bsFFFFFF has quit [Remote host closed the connection]
atka has quit [Quit: WeeChat 4.4.2]
naoki has joined #riscv
zBeeble has joined #riscv
levitating_ has quit [Remote host closed the connection]
levitating_ has joined #riscv
mlw has quit [Remote host closed the connection]
Stat_headcrabbed has quit [Quit: Stat_headcrabbed]
levitating__ has joined #riscv
levitating_ has quit [Ping timeout: 276 seconds]
jmontleon has quit [Quit: Leaving]
___nick___ has quit [Ping timeout: 265 seconds]
vagrantc has quit [Quit: leaving]
test925 has joined #riscv
test924 has quit [Ping timeout: 265 seconds]
CipherLab has quit [Ping timeout: 248 seconds]
Armand|Desktop has joined #riscv
psydroid has quit [Quit: KVIrc 5.0.0 Aria http://www.kvirc.net/]
cow321 has quit [Ping timeout: 255 seconds]
CryptLab has joined #riscv
lagash has quit [Remote host closed the connection]
cow321 has joined #riscv
hwspeedy has quit [Ping timeout: 252 seconds]
hwspeedy has joined #riscv
raym has quit [Ping timeout: 252 seconds]
aredridel7 has joined #riscv
aredridel has quit [Ping timeout: 252 seconds]
Forty-Bot has quit [Ping timeout: 252 seconds]
aredridel7 is now known as aredridel
raym has joined #riscv
n_crm_ has joined #riscv
n_crm has quit [Ping timeout: 252 seconds]
alperak has quit [Quit: Connection closed for inactivity]
Forty-Bot has joined #riscv
levitating__ is now known as levitating
danilogondolfo has quit [Remote host closed the connection]
Noisytoot has joined #riscv
hwspeedy has quit [Read error: Connection reset by peer]
Noisytoot has quit [Quit: ZNC 1.9.1 - https://znc.in]
Noisytoot has joined #riscv
jedesa has quit [Remote host closed the connection]
fuwei has quit [Ping timeout: 252 seconds]