Re: amdgpu 100% CPU usage causing freeze 1002:15d8

[Marco Moock <mm@dorfdsl.de>]

Am 16.01.2025 um 11:21:11 Uhr schrieb Alex Deucher:

> On Wed, Jan 15, 2025 at 4:02 PM Marco Moock <mm@dorfdsl.de> wrote:
> >
> > Am Wed, 15 Jan 2025 15:27:00 -0500
> > schrieb Alex Deucher <alexdeucher@gmail.com>:
> >  
> > > On Wed, Jan 15, 2025 at 3:22 PM Marco Moock <mm@dorfdsl.de>
> > > wrote:  
> > > >
> > > > Am Wed, 15 Jan 2025 16:08:34 +0100
> > > > schrieb Marco Moock <mm@dorfdsl.de>:
> > > >  
> > > > > I assume it was 6.12.6, but Debian doesn't have the old
> > > > > packages anymore and it has been purged from my system
> > > > > already.  
> > > >
> > > > I've now tried 6.12.6, same situation.
> > > >
> > > > Any further ideas what could cause this?  
> > >
> > > Can you provide more details about what you are seeing?  What
> > > does `ps aux` or `top` show as using all of the CPU time?  
> >
> > I saw
> >    2977 root      20   0       0      0      0 R  99,3   0,0
> > 5:18.68 kworker/u16:39+amdgpu-reset-dev
> >
> > But the system is almost unusable, it takes seconds to print the
> > characters in terminal when connecting from a remote machine. Local,
> > the system doesn't care about keyboard anymore, except Sysrq.
> > Switching to another tty wasn't possible.
> >
> > In some cases, even the sysrq keystroke won't be recognized and I
> > need to use the reset switch on the case.  
> 
> Can you get the dmesg output when this happens?  Might be easier to
> get it over a remote connection like ssh if possible.

Jan 15 20:40:26 ryz kernel: amdgpu 0000:08:00.0: amdgpu: Dumping IP
State

This is the only message that is related to the problem. 
After that are some firewall messages, I doubt that they are useful to
be posted here.

-- 
Gruß
Marco