Am 04.05.19 um 12:51 schrieb Mikhail Gavrilov:
On Sat, 4 May 2019 at 12:33, Christian König
<ckoenig.leichtzumerken@xxxxxxxxx> wrote:
Hi Mikhail,
well short answer is not at all :)
After the GPU reset happened all waves should be gone and the gfx block
in a clean state again.
What you need to do is to disable automatic reset by setting
amdgpu.lockup_timeout=-1 on the kernel command line and then inspect the
system over ssh.
This is not convenient, because:
- requires an additional computer.
- after the GPU freezes, the chances of correctly restarting the
computer tend to zero.
For me, as a bug hunter, it would be more convenient if all the dumps
were automatically dropped before resetting the GPU to specified
directory.
Yeah, but for most end users we need to get the GPU working as fast as
possible on a lockup.
Saving all the state (which actually can be a couple of gigabytes if you
include all textures etc..) is not really an option then.
What we could probably do rather easily is to add a function to run a
script instead of a GPU reset on lockup detection.
Regards,
Christian.
But thanks anyway.
Here is a new bug report: https://bugs.freedesktop.org/show_bug.cgi?id=110605
--
Best Regards,
Mike Gavrilov.
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
