00:00
damian101 has quit [Ping timeout: 246 seconds]
00:00
vagrantc has quit [Quit: leaving]
00:51
zBeeble has quit [Read error: Connection reset by peer]
00:52
zBeeble has joined #riscv
01:17
hwspeedy has quit [Read error: Connection reset by peer]
01:22
Tenkawa has quit [Quit: Was I really ever here?]
01:43
test924 has joined #riscv
01:56
BootLayer has joined #riscv
02:16
X-Scale has quit [Quit: Client closed]
02:25
atka has quit [Ping timeout: 265 seconds]
03:07
hexdump0815 has quit [Ping timeout: 248 seconds]
03:09
hexdump0815 has joined #riscv
03:10
Armand|T420 has quit [Ping timeout: 265 seconds]
03:14
levitating has quit [Remote host closed the connection]
03:30
atka has joined #riscv
03:40
JanC has quit [Ping timeout: 265 seconds]
03:40
JanC has joined #riscv
03:59
Starfoxxes has quit [Ping timeout: 244 seconds]
04:08
jacklsw has joined #riscv
04:10
JanC is now known as Guest1029
04:10
Guest1029 has quit [Killed (silver.libera.chat (Nickname regained by services))]
04:10
JanC has joined #riscv
04:14
JanC_ has joined #riscv
04:14
JanC has quit [Killed (erbium.libera.chat (Nickname regained by services))]
04:14
JanC_ is now known as JanC
04:20
jobol has joined #riscv
04:23
JanC_ has joined #riscv
04:24
JanC has quit [Ping timeout: 260 seconds]
04:27
JanC has joined #riscv
04:28
JanC_ has quit [Ping timeout: 265 seconds]
04:29
heat has quit [Ping timeout: 248 seconds]
04:30
BootLayer has quit [Quit: Leaving]
04:33
damian101 has joined #riscv
04:37
JanC has quit [Ping timeout: 252 seconds]
04:39
JanC has joined #riscv
04:40
TMM has joined #riscv
04:57
mlw has joined #riscv
05:33
indy has quit [Ping timeout: 276 seconds]
05:54
JanC_ has joined #riscv
05:54
JanC is now known as Guest7191
05:54
Guest7191 has quit [Killed (molybdenum.libera.chat (Nickname regained by services))]
05:54
JanC_ is now known as JanC
06:08
seasharp has joined #riscv
06:09
seasharp_ has quit [Ping timeout: 245 seconds]
06:11
danilogondolfo has quit [Read error: Connection reset by peer]
06:11
danilogondolfo has joined #riscv
06:12
davidlt_ has joined #riscv
06:14
JanC_ has joined #riscv
06:14
JanC has quit [Killed (tantalum.libera.chat (Nickname regained by services))]
06:14
JanC_ is now known as JanC
06:16
ldevulder has joined #riscv
06:17
JanC_ has joined #riscv
06:18
JanC is now known as Guest9364
06:18
JanC_ is now known as JanC
06:19
naoki has quit [Quit: naoki]
06:19
Guest9364 has quit [Ping timeout: 252 seconds]
06:25
levitating has joined #riscv
06:34
levitating has quit [Remote host closed the connection]
06:34
levitating has joined #riscv
06:36
levitating_ has joined #riscv
06:36
JanC_ has joined #riscv
06:36
JanC has quit [Ping timeout: 252 seconds]
06:36
JanC_ is now known as JanC
06:39
levitating has quit [Ping timeout: 265 seconds]
06:51
atka has quit [Ping timeout: 265 seconds]
06:58
atka has joined #riscv
07:00
JanC has quit [Ping timeout: 272 seconds]
07:02
JanC has joined #riscv
07:07
JanC_ has joined #riscv
07:07
JanC is now known as Guest781
07:07
Guest781 has quit [Killed (calcium.libera.chat (Nickname regained by services))]
07:07
JanC_ is now known as JanC
07:10
JanC_ has joined #riscv
07:10
JanC has quit [Killed (tantalum.libera.chat (Nickname regained by services))]
07:10
JanC_ is now known as JanC
07:36
levitating has joined #riscv
07:36
levitating_ has quit [Ping timeout: 272 seconds]
07:38
alperak has joined #riscv
08:05
jjido has joined #riscv
08:13
davidlt has joined #riscv
08:25
mlw has quit [Read error: Connection reset by peer]
08:28
mlw has joined #riscv
08:53
jjido has quit [Quit: My laptop has gone to sleep. ZZZzzz…]
09:01
ncopa has quit [Changing host]
09:01
ncopa has joined #riscv
09:02
X-Scale has joined #riscv
09:08
Stat_headcrabbed has joined #riscv
09:31
coldfeet has joined #riscv
09:31
jacklsw has quit [Quit: Back to the real world]
09:41
Stat_headcrabbed has quit [Quit: Stat_headcrabbed]
09:43
Stat_headcrabbed has joined #riscv
10:15
coldfeet has quit [Remote host closed the connection]
10:24
davidlt_ has quit [Ping timeout: 244 seconds]
10:24
davidlt has quit [Ping timeout: 252 seconds]
11:11
davidlt_ has joined #riscv
11:12
davidlt has joined #riscv
11:22
heat has joined #riscv
11:44
naoki has joined #riscv
11:53
somlo_ is now known as somlo
12:17
naoki has quit [Quit: naoki]
12:28
X-Scale has quit [Quit: Client closed]
12:31
zBeeble has quit [Ping timeout: 272 seconds]
12:35
zBeeble has joined #riscv
12:46
Tenkawa has joined #riscv
12:54
levitating has quit [Remote host closed the connection]
13:15
X-Scale has joined #riscv
13:36
psydroid has joined #riscv
13:37
___nick___ has joined #riscv
14:02
levitating has joined #riscv
14:17
hwspeedy has joined #riscv
14:23
andyc has joined #riscv
14:41
X-Scale has quit [Ping timeout: 256 seconds]
14:44
zBeeble42 has joined #riscv
14:45
zBeeble has quit [Read error: Connection reset by peer]
14:45
levitating has quit [Remote host closed the connection]
14:49
BootLayer has joined #riscv
14:57
coldfeet has joined #riscv
15:13
<
mps >
Tenkawa: do you still have high load on bananapi f3?
15:13
<
Tenkawa >
mps: haven't worked on it in a few days... depends on how I set it up
15:14
<
mps >
which scheduler you use
15:14
<
Tenkawa >
tried all of them
15:14
<
Tenkawa >
are you using a nvme root?
15:15
<
Tenkawa >
until you do your testing is irrelevant
15:15
<
mps >
well, I found high load is with schedutil, changing to performance or conservative load is 0.00
15:16
<
Tenkawa >
This happens on all schedulers with nvme drives
15:16
<
mps >
did you tested
15:16
<
Tenkawa >
I "started" with performace
15:16
<
Tenkawa >
er performance
15:19
<
ncopa >
i observed the high cpu load today
15:19
<
ncopa >
with the bananapi bpi-f3
15:20
<
ncopa >
i run docker with data storage on nvme
15:20
<
ncopa >
use it as a gitlab runner
15:21
<
Tenkawa >
yep. We found the
15:21
<
davidlt_ >
We noticed that high loads on idle exist, and that comes from mailbox driver.
15:21
<
Tenkawa >
davidlt_: its mailbox + remoteproc
15:21
<
davidlt_ >
If you disable mailbox loads go down, yet to no longer can go "turbo mode" to 1.8GHz on M1.
15:21
<
Tenkawa >
but fixing it makes the unit unstable
15:22
<
davidlt_ >
Someone on Fedora/RISCV Matrix channel has a workaround/patch, but is waiting to get account to gitee.com
15:22
<
ncopa >
is this reported upstream?
15:22
<
Tenkawa >
I can consistently lock it up in about 15 seconds now
15:22
<
ncopa >
i tried to create account on gitee.com but got 500
15:22
<
Tenkawa >
ncopa: they are on holiday for aother week
15:23
<
Tenkawa >
If you mean Bianbu
15:23
<
Tenkawa >
We really need to find resources to try to upstream it....
15:23
<
mps >
davidlt_: alpine kernel have disabled these options
15:24
<
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?).
15:24
<
Tenkawa >
Disabling them works but it still will lockup nvme
15:24
<
Tenkawa >
davidlt_: exactly
15:25
<
Tenkawa >
there's something badly io routed too....
15:25
<
davidlt_ >
We have 4 (or more) boards connected in Fedora/RISCV Koji farm. I don't think we ever saw NVMe lockups or similar.
15:25
<
mps >
Tenkawa: ncopa use kernel on nvme with these disabled
15:25
<
Tenkawa >
mps: and he just stated he sees the same high load
15:26
<
Tenkawa >
[11:19:42] ncopa: i observed the high cpu load today
15:26
<
mps >
Tenkawa: yes, but when changing scheduler load on his machine goes down
15:26
<
ncopa >
PID PPID USER STAT VSZ %VSZ CPU %CPU COMMAND
15:26
<
ncopa >
117 2 root RW 0 0% 6 12% [sugov:0]
15:26
<
mps >
he can confirm
15:27
<
ncopa >
was a process named [sugov:0] that too 100% of one cpu
15:27
<
ncopa >
google told me it is related the cpu scheduler
15:27
<
mps >
right, I found this last night
15:27
<
ncopa >
when switching to "performance" CPU scheduler it went down
15:28
<
ncopa >
but i dont know yet if it will re-appear
15:28
<
jn >
"SUGOV stands for SchedUtil GOVernor.", TIL
15:28
<
Tenkawa >
Thats a governor thread... if you
15:28
<
Tenkawa >
er if you don't have the right scheduling options set it can spin
15:28
<
Tenkawa >
there's dt options that also go with the scheduler subsystem
15:29
<
Tenkawa >
not just "which" scheduler
15:29
<
davidlt_ >
I assume it went away because you asked for "performance", and thus probably doesn't need to talk to PM that much.
15:29
<
mps >
jn: thanks, I wondered what is this strange name
15:29
<
mps >
davidlt_: also conservative works fine
15:30
<
davidlt_ >
Yeah, anyways it's a bug in vendor kernel.
15:30
<
Tenkawa >
davidlt_: Yeah I am curious about PM too... I turn it all off
15:30
ldevulder has quit [Quit: Leaving]
15:30
<
Tenkawa >
davidlt_: indeed... many...
15:31
<
mps >
wonder why they touch schedutil at all
15:31
<
davidlt_ >
Yeah, Jason files 10+ issues while trying to compile their kernel for Fedora.
15:31
<
Tenkawa >
I thought Rockchip on Arm and Starfive chips were "fun" lol
15:31
<
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.
15:31
<
ncopa >
turns out mps was right
15:31
<
ncopa >
i bumped the kernel to 6.6.53 also
15:31
vagrantc has joined #riscv
15:32
<
davidlt_ >
Well, wait 1-2 years and we might be able to boot upstream :)
15:32
<
Tenkawa >
Yeah mine is on lol
15:32
<
mps >
to add to ncopa message, our (alpine) kernel boot fine on lpi3a also
15:32
davidlt_ has quit [Quit: Leaving]
15:34
<
ncopa >
in case someone wants compare how the conflicts with bianbu kernel was solved
15:35
<
mps >
also we have ready-made images for sd card
15:36
<
mps >
and ncopa have better one but I forgot where
15:37
<
ncopa >
i need to recreate it with latest kernel
15:38
<
mps >
ncopa: maybe wait a little till I push opensbi and u-boot to aports
15:38
<
mps >
then we will complete alpine solution for bpif3 and lpi3a
15:39
jmontleon has joined #riscv
15:49
billchenchina- has joined #riscv
15:51
ZipCPU has joined #riscv
16:06
hwspeedy has quit [Read error: Connection reset by peer]
16:16
levitating has joined #riscv
16:24
psydroid has joined #riscv
16:28
davidlt has quit [Ping timeout: 265 seconds]
16:30
jobol has quit [Quit: Leaving]
16:35
davidlt has joined #riscv
16:50
___nick___ has joined #riscv
16:50
___nick___ has quit [Client Quit]
16:53
___nick___ has joined #riscv
16:53
billchenchina- has quit [Remote host closed the connection]
17:00
<
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
17:02
<
mps >
remoteproc is riscv32 and that is all I know about it
17:03
<
Tenkawa >
Yeah not very useful in most envs
17:04
<
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
17:04
bsFFFFFF has joined #riscv
17:06
<
Tenkawa >
(... or semi/non-functional)
17:09
bsFFFFFF has quit [Ping timeout: 245 seconds]
17:10
bsFFFFFF has joined #riscv
17:10
<
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
17:11
<
mps >
I hope ncopa will test it on board with nvme and tell us
17:11
<
mps >
or it could be because I use new opensbi and u-boot
17:12
Noisytoot has joined #riscv
17:14
<
Tenkawa >
mps: what kernel version?
17:15
<
mps >
mainline 6.6.53 with bianbu patches
17:15
coldfeet has quit [Remote host closed the connection]
17:15
<
Tenkawa >
Nod wanted to make sure you were using 6.6
17:16
X-Scale has joined #riscv
17:16
<
Tenkawa >
6.1 apparently doesn't have this problem
17:16
<
Tenkawa >
(I didn't test 6.1 more than a few hours so I can't confirm)
17:16
<
mps >
I didn't used 6.1 much, just to get 6.6 booting
17:20
<
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
17:25
<
mps >
that would be nice to have
17:27
davidlt has quit [Ping timeout: 260 seconds]
17:37
Noisytoot has quit [Ping timeout: 246 seconds]
17:38
<
Tenkawa >
mps: yeah... just having an empty socket and no chip is just... mean
17:39
<
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
17:40
<
Tenkawa >
Are you sure there's one soldered on?
17:40
<
Tenkawa >
Noone I know has had one yet
17:40
<
Tenkawa >
only the 2gb ram ones have
17:40
<
Tenkawa >
and those are rare
17:40
<
mps >
my board is 2GB RAM
17:45
levitating has quit [Remote host closed the connection]
17:45
levitating has joined #riscv
17:55
<
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.
17:55
levitating_ has joined #riscv
17:56
<
Tenkawa >
jmontleon: you have to chainload it from microsd
17:58
levitating has quit [Ping timeout: 252 seconds]
18:01
<
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
18:01
<
mps >
s/load if/load of/
18:03
<
Tenkawa >
That would make sense... different io path
18:03
<
Tenkawa >
I haven't used the emmc for anything... too easy to crash it and be a pain to fix
18:04
mlw has quit [Ping timeout: 265 seconds]
18:06
jedesa has quit [Remote host closed the connection]
18:06
yaneti has joined #riscv
18:07
davidlt has joined #riscv
18:16
jedesa has joined #riscv
18:20
BootLayer has quit [Quit: Leaving]
18:26
frkazoid333 has quit [Ping timeout: 252 seconds]
18:37
frkazoid333 has joined #riscv
18:39
frkazoid333 has quit [Remote host closed the connection]
18:39
frkazoid333 has joined #riscv
18:40
frkazoid333 has quit [Remote host closed the connection]
18:43
TMM has joined #riscv
18:43
andyc has quit [Quit: Connection closed for inactivity]
18:45
levitating_ has quit [Ping timeout: 252 seconds]
18:49
levitating_ has joined #riscv
18:52
mlw has joined #riscv
18:53
jjido has joined #riscv
19:02
hwspeedy has joined #riscv
19:05
zBeeble42 has quit [Ping timeout: 248 seconds]
19:12
jjido has quit [Quit: My laptop has gone to sleep. ZZZzzz…]
19:27
davidlt has quit [Ping timeout: 276 seconds]
19:33
bsFFFFFF has quit [Remote host closed the connection]
19:34
atka has quit [Quit: WeeChat 4.4.2]
19:37
naoki has joined #riscv
19:41
zBeeble has joined #riscv
19:47
levitating_ has quit [Remote host closed the connection]
19:48
levitating_ has joined #riscv
19:50
mlw has quit [Remote host closed the connection]
19:51
Stat_headcrabbed has quit [Quit: Stat_headcrabbed]
19:54
levitating__ has joined #riscv
19:57
levitating_ has quit [Ping timeout: 276 seconds]
20:00
jmontleon has quit [Quit: Leaving]
20:04
___nick___ has quit [Ping timeout: 265 seconds]
20:16
vagrantc has quit [Quit: leaving]
20:21
test925 has joined #riscv
20:24
test924 has quit [Ping timeout: 265 seconds]
20:29
CipherLab has quit [Ping timeout: 248 seconds]
20:29
Armand|Desktop has joined #riscv
21:07
cow321 has quit [Ping timeout: 255 seconds]
21:07
CryptLab has joined #riscv
21:17
lagash has quit [Remote host closed the connection]
21:25
cow321 has joined #riscv
21:28
hwspeedy has quit [Ping timeout: 252 seconds]
21:28
hwspeedy has joined #riscv
21:32
raym has quit [Ping timeout: 252 seconds]
21:34
aredridel7 has joined #riscv
21:35
aredridel has quit [Ping timeout: 252 seconds]
21:35
Forty-Bot has quit [Ping timeout: 252 seconds]
21:35
aredridel7 is now known as aredridel
21:39
raym has joined #riscv
21:43
n_crm_ has joined #riscv
21:44
n_crm has quit [Ping timeout: 252 seconds]
21:48
alperak has quit [Quit: Connection closed for inactivity]
21:49
Forty-Bot has joined #riscv
22:10
levitating__ is now known as levitating
22:16
danilogondolfo has quit [Remote host closed the connection]
22:33
Noisytoot has joined #riscv
23:24
hwspeedy has quit [Read error: Connection reset by peer]
23:28
Noisytoot has joined #riscv
23:41
jedesa has quit [Remote host closed the connection]
23:49
fuwei has quit [Ping timeout: 252 seconds]