| View previous topic :: View next topic |
| Author |
Message |
c2
n00b
Joined: 14 Mar 2025
Posts: 17
|
 Posted: Sat Mar 29, 2025 8:21 pm Post subject: extreemly high gpu useage on idle (3 ghz, 97% GFX, 200w) |
 |
|
hello i have a 7900 xtx, i have been pulling around 200w somewhat speraticly and getting to 3.ghz for somewhat sustianed times, the longest was 7 minutes the shortest are 6-20 seconds. by checking amdgpu_top it is all gfx. this persits across boots. this boot i had a memory leak that somehwat crashed kde plasma untill the kerrnel kill spectical (kde screen shot tool). then my gpu (36 of uptime) started working normaly. also note when ever i play media on my web browser (brave) gfx useage would always (expect for the first 5 minutes affter boot) would be at 90%, this is somewhat sepreate from the orgianl high gfx useage as that would happen even when brvae is closed and killed. i checled brave://gpu and it listed hardware decode as supported but now affter the memeory leak it is now listed as unsported. for refence i overclocked this card with lact but i disbaled the service with systemctl so idk how the overclock is still aplying, tho ppfeaturemask=0xffffffff is still enabled.
if you have any idea of whats happening please tell me, i've skimmed journalctl and it has shown nothing of intrest
| Code: |
c2@gentoobtw ~ $ fastfetch
-/oyddmdhs+:. c2@gentoobtw
-odNMMMMMMMMNNmhy+-` ------------
-yNMMMMMMMMMMMNNNmmdhy+- OS: Gentoo Linux x86_64
`omMMMMMMMMMMMMNmdmmmmddhhy/` Kernel: Linux 6.13.9-gentoo-dist
omMMMMMMMMMMMNhhyyyohmdddhhhdo` Uptime: 54 mins
.ydMMMMMMMMMMdhs++so/smdddhhhhdm+` Packages: 1853 (emerge), 6 (flatpak-user)
oyhdmNMMMMMMMNdyooydmddddhhhhyhNd. Shell: bash 5.2.37
:oyhhdNNMMMMMMMNNNmmdddhhhhhyymMh Display (XV275K): 3840x2160 @ 60 Hz (as 3548x1996) in 27" [External]
.:+sydNMMMMMNNNmmmdddhhhhhhmMmy Display (LG FULL HD): 1080x1920 @ 60 Hz in 22" [External]
/mMMMMMMNNNmmmdddhhhhhmMNhs: Display (Odyssey G7): 3840x2160 @ 120 Hz in 31" [External, HDR] *
`oNMMMMMMMNNNmmmddddhhdmMNhs+` Display (LG FULL HD): 1080x1920 @ 60 Hz in 22" [External]
`sNMMMMMMMMNNNmmmdddddmNMmhs/. DE: KDE Plasma 6.3.3
/NMMMMMMMMNNNNmmmdddmNMNdso:` WM: KWin (Wayland)
+MMMMMMMNNNNNmmmmdmNMNdso/- WM Theme: Infinity-Solid-Aurorae-6
yMMNNNNNNNmmmmmNNMmhs+/-` Theme: Breeze (Custum_blues_and_purples) [Qt], Breeze-Dark [GTK2], Breeze [GTK3]
/hMMNNNNNNNNMNdhs++/-` Icons: Vivid-Dark-Icons [Qt], Vivid-Dark-Icons [GTK2/3/4]
`/ohdmmddhys+++/:.` Font: Noto Sans (10pt) [Qt], Noto Sans (10pt) [GTK2/3/4]
`-//////:--. Cursor: Vivid-Dark-Icons (24px)
Terminal: konsole 24.12.3
CPU: AMD Ryzen 7 7800X3D (16) @ 5.05 GHz
GPU 1: AMD Radeon RX 7900 XTX [Discrete]
GPU 2: AMD Raphael [Integrated]
Memory: 9.63 GiB / 93.45 GiB (10%)
Swap: 750.52 MiB / 16.00 GiB (5%)
Disk (/): 845.63 GiB / 914.07 GiB (93%) - xfs
Disk (/run/media/hdd): 8.28 TiB / 10.83 TiB (76%) - ext4
Disk (/run/media/nvme2): 143.36 GiB / 232.88 GiB (62%) - btrfs
Disk (/run/media/ssds): 44.27 GiB / 476.46 GiB (9%) - xfs
Local IP (eno1): 10.0.0.179/24
Locale: en_US.UTF-8
c2@gentoobtw ~ $
|
|
|
| Back to top |
|
 |
c2
n00b
Joined: 14 Mar 2025
Posts: 17
|
| Posted: Sat Mar 29, 2025 9:47 pm Post subject: |
|
|
| i complety disabled ppfeaturemask yet my gpu is still hitting 3 ghz when stock is 2.53 |
|
| Back to top |
|
|
NeddySeagoon
Administrator
Joined: 05 Jul 2003
Posts: 55102
Location: 56N 3W
|
| Posted: Sat Mar 29, 2025 9:53 pm Post subject: |
|
|
c2,
Put dmesg onto a pastebin, lets see if you are actually using the right video driver.
It will show why not, if not.
_________________
Regards,
NeddySeagoon
Computer users fall into two groups:-
those that do backups
those that have never had a hard drive fail. |
|
| Back to top |
|
|
c2
n00b
Joined: 14 Mar 2025
Posts: 17
|
| Posted: Sat Mar 29, 2025 10:11 pm Post subject: |
|
|
| NeddySeagoon wrote: | c2,
Put dmesg onto a pastebin, lets see if you are actually using the right video driver.
It will show why not, if not. |
i jsut rebooted and disbaled my igpu which i was running 2 displays off of and everything is now workign as it should, but i am still worried that is was working like this to begine with
pastbin (dmesg current boot)
https://pastebin.com/43kmjjfp
pastbin (journalctl -b -1| grep kernel)
https://pastebin.com/5mxHqXDb |
|
| Back to top |
|
|
c2
n00b
Joined: 14 Mar 2025
Posts: 17
|
| Posted: Sun Mar 30, 2025 2:41 am Post subject: |
|
|
so i my whole desktop froze went into a tty termian threw ctrl + alt + fx checked some logs and what not ran htop saw my gui prosses where still running then affter i switched back whats hould have been my display i got no video out for the rest of that boot. with no video out i opened a new tty terminal and ran the reboot command.
here are some journalctl logs
| Code: |
c2@gentoobtw ~ $ journalctl -b -1 -p err
Mar 29 18:13:27 gentoo kernel: hub 10-0:1.0: config failed, hub doesn't have any ports! (err -19)
Mar 29 18:13:28 gentoobtw kernel: Bluetooth: hci0: No support for _PRR ACPI method
Mar 29 18:13:28 gentoobtw (udev-worker)[773]: event15: Failed to call EVIOCSKEYCODE with scan code 0x7c, and key code 190: Invalid argument
Mar 29 18:13:29 gentoobtw kernel: amdgpu: Overdrive is enabled, please disable it before reporting any bugs unrelated to overdrive.
Mar 29 18:13:49 gentoobtw sddm-helper[1220]: gkr-pam: unable to locate daemon control file
Mar 29 18:15:28 gentoobtw systemd-networkd-wait-online[848]: Timeout occurred while waiting for network connectivity.
Mar 29 18:15:28 gentoobtw systemd[1]: Failed to start Wait for Network to be Configured.
Mar 29 22:24:48 gentoobtw kernel: amdgpu 0000:03:00.0: [drm] *ERROR* [CRTC:91:crtc-3] flip_done timed out
Mar 29 22:25:07 gentoobtw kernel: amdgpu 0000:03:00.0: [drm] *ERROR* flip_done timed out
Mar 29 22:25:07 gentoobtw kernel: amdgpu 0000:03:00.0: [drm] *ERROR* [CRTC:91:crtc-3] commit wait timed out
Mar 29 22:25:17 gentoobtw kernel: amdgpu 0000:03:00.0: [drm] *ERROR* flip_done timed out
Mar 29 22:25:17 gentoobtw kernel: amdgpu 0000:03:00.0: [drm] *ERROR* [PLANE:88:plane-9] commit wait timed out
Mar 29 22:30:36 gentoobtw systemd-coredump[204471]: Failed to send coredump datagram: Broken pipe
Mar 29 22:30:37 gentoobtw systemd-coredump[204517]: Failed to send coredump datagram: Broken pipe
Mar 29 22:30:37 gentoobtw systemd-coredump[204519]: Failed to send coredump datagram: Broken pipe
Mar 29 22:30:44 gentoobtw kernel: watchdog: watchdog0: watchdog did not stop!
c2@gentoobtw ~ $
|
and these 2 repeated a bunch towards the end
| Code: |
Mar 29 22:30:07 gentoobtw kwin_wayland_wrapper[1322]: kwin_wayland_drm: No drm events for gpu "/dev/dri/card0" within last 1 second
Mar 29 22:30:07 gentoobtw kwin_wayland_wrapper[1322]: kwin_wayland_drm: Pageflip timed out! This is a bug in the amdgpu kernel driver
|
|
|
| Back to top |
|
|
NeddySeagoon
Administrator
Joined: 05 Jul 2003
Posts: 55102
Location: 56N 3W
|
| Posted: Sun Mar 30, 2025 7:28 pm Post subject: |
|
|
c2,
Your logs sow several kernel Oops on going to suspend/hibernate.
Does it only go wrong when you resume?
With | Code: | | Memory: 9.63 GiB / 93.45 GiB (10%) |
a reboot is probably faster than a hibernate.
Thats a lot of RAM to process.
_________________
Regards,
NeddySeagoon
Computer users fall into two groups:-
those that do backups
those that have never had a hard drive fail. |
|
| Back to top |
|
|
|
Kernel & Hardware
