Hard lockups with ROCM

[Daniel Kasak]

On Thu, May 16, 2019 at 11:43 AM Alex Deucher <alexdeucher at gmail.com> wrote:

> On Wed, May 15, 2019 at 8:33 PM Daniel Kasak <d.j.kasak.dk at gmail.com>
> wrote:
> >
> > On Mon, May 13, 2019 at 11:44 AM Daniel Kasak <d.j.kasak.dk at gmail.com>
> wrote:
> >>
> >> Hi all. I had version 2.2.0 of the ROCM stack running on a 5.0.x and
> 5.1.0 kernel. Things were going great with various boinc GPU tasks. But
> there is a setiathome GPU task which reliably gives me a hard lockup within
> about 30 minutes of running. I actually had to do *two* emergency
> re-installs over the past week. Perhaps part of this was my fault ( running
> btrfs with lzo compression on my root partition ... ). But absolutely part
> of this was the hard lockups. I've tested all kinds of other things ( eg
> rebuilding lots of stuff under Gentoo ) ... I don't have a general
> stability issue even under hours of high load. But after restarting boinc
> with that same setiathome task ... <bang>!
> >>
> >> If someone wants me to sacrifice another installation, they can point
> me to instructions for trying to gather more information.
> >>
> >> Anyway ... perhaps more work around detecting and recovering from GPU
> lockups is in order?
> >>
> >> Dan
> >
> >
> > <sigh>
> >
> > That's what I was afraid of :(
>
> Not sure what you were afraid of.  I don't think anyone has looked at
> setiathome on ROCm.  I'd suggest filing a bug
> (https://bugs.freedesktop.org) and attaching your dmesg output and
> xorg log (if using X).  If there is a GPU reset, note that you will
> need to restart your desktop environment because currently neither
> glamor or any compositors support GL robustness extensions to reset
> their contexts after a GPU reset.
>
> Alex
>

Hi Alex. dmesg output is not available ... this is a *hard* lockup. I need
to power-cycle after it happens ( ALT + SysRq + { S , U , B } doesn't even
work ). That's why I asked for instructions to possibly gather more info. I
did check the xorg log after I did an emergency export of my filesystem ...
nothing of interest in there. It seems like I currently don't really have
enough info to make a bug report worthwhile.

Dan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20190516/415ff2b8/attachment.html>