Re: [PATCH v6 00/31] Fair(er) DRM scheduler

[Philipp Stanner <phasta@mailbox.org>]

On Thu, 2026-02-12 at 09:56 +0000, Tvrtko Ursulin wrote:
> 
> On 11/02/2026 11:08, Philipp Stanner wrote:
> > On Wed, 2026-01-28 at 11:07 +0000, Tvrtko Ursulin wrote:
> > > ** NOTE:
> > >     First three patches have been already reviewed and are conceptualy
> > >     independent. But as the code conflicts, I am including them while waiting for
> > >     them to be merged via amd-next, and until they percolate back to drm-tip, in
> > >     order to avoid having to maintain two separate patch series.
> > 
> > 
> > So your intention with this v6 is just to get more reviews? What is the
> > purpose?
> > 
> > And since the plan is supposedly that the drm_sched maintainers take
> > it, when will they know that it's ready now?
> > 
> > Can we agree on delaying a v7 until all lights are green?
> 
> I am waiting on Christian to merge the first three patches via amd-next. 
> That is pending for a month now and in the meantime I did not want to
> send this series and have someone tell me it does not apply. If by a 
> miracle someone actually went to try and give it a spin.

Then praised be the Lord, because this miracle has happened and I was
about to pull this series onto my machines and give it some more
testing and last reviewish look-throughs. That's why I asked about
applicability. Since we basically agree to get it in :)

> For the moment I don't think this is a problem for this series since 
> there are so many more patches still pending to review. And based on the 
> past experience you will not be merging it any time soon. As there are 
> no design conflicts between the two, the review can progress just fine 
> ignoring the first three patches.
> 
> > For the future, I think the more canonical (and less confusing) way to
> > handle situations like this is not to include foreign patches into a
> > single-topic patch series, but to hint in the cover letter at the
> > situation and provide links: "Series is blocked by [1], [2]".
> 
> Again, like that it wouldn't build and no one would be able to test it. 
> For now just skip the first three and focus on the rest and hopefully by 
> v7 I will be able to drop those.

I'd say postpone v7 until the merge conflicts are resolved. Maybe ping
a few of the driver maintainers. I'll also look through it one more
time.

Then hopefully v7 will be mergeable.
(and please no unavoidable changes like merging or adding patches for
v7, except for addressing review feedback)


P.