(In reply to Chris Wilson from comment #226)
> (In reply to Martin Steigerwald from comment #225)
> > Chris, you referred me to this bug as I reported
> >
> > Bug 90835 - [4.1-rc6] gpu hang: ecode 6:-1:0x00000000, Kicking stuck
> > semaphore on render ring
> >
> > I skimmed through it and it appears that there are some patches to test? But
> > I am not sure which ones these are. Can you or someone else enlighten me?
>
> There's likely a modest improvement in 4.2.
Nice.
> > Also I note that I still use
> >
> > Option "AccelMethod" "uxa"
> >
> > and I have
> >
> > martin@merkaba:~> cat /etc/modprobe.d/i915-kms.conf
> > options i915 modeset=1 i915_enable_rc6=7
>
> Fortuitously that dangerous option doesn't do anything for your kernel.
Well I found out why, I compiled i915 into the kernel it seems, at least I don´t have an i915 module in lsmod. But also i915.i915_enable_rc6=7 on kernel command line does not seem to have any effect. I removed the option.
> > ffffffff813a4b0e
> > thus maximum energy saving. But according to powertop it never enters the
> > highest sleep state anyway.
> >
> > I will remove the AccelMethod setting now and see whether it helps. If not,
> > I downgrade to 4.1-rc4 for now, as issues have been at least much less
> > frequent with it.
>
> Purely circumstantial.
Since using SNA I didn´t see a GPU hang so far. Too early to say for sure, but it seems something in UXA may have triggered it more easily.
(In reply to Chris Wilson from comment #226)
> (In reply to Martin Steigerwald from comment #225)
> > Chris, you referred me to this bug as I reported
> >
> > Bug 90835 - [4.1-rc6] gpu hang: ecode 6:-1:0x00000000, Kicking stuck
> > semaphore on render ring
> >
> > I skimmed through it and it appears that there are some patches to test? But
> > I am not sure which ones these are. Can you or someone else enlighten me?
>
> There's likely a modest improvement in 4.2.
Nice.
> > Also I note that I still use d/i915- kms.conf
> >
> > Option "AccelMethod" "uxa"
> >
> > and I have
> >
> > martin@merkaba:~> cat /etc/modprobe.
> > options i915 modeset=1 i915_enable_rc6=7
>
> Fortuitously that dangerous option doesn't do anything for your kernel.
Well I found out why, I compiled i915 into the kernel it seems, at least I don´t have an i915 module in lsmod. But also i915.i915_ enable_ rc6=7 on kernel command line does not seem to have any effect. I removed the option.
> > ffffffff813a4b0e
> > thus maximum energy saving. But according to powertop it never enters the
> > highest sleep state anyway.
> >
> > I will remove the AccelMethod setting now and see whether it helps. If not,
> > I downgrade to 4.1-rc4 for now, as issues have been at least much less
> > frequent with it.
>
> Purely circumstantial.
Since using SNA I didn´t see a GPU hang so far. Too early to say for sure, but it seems something in UXA may have triggered it more easily.