[RFC v3 1/8] gpu: rfc: Proposal for a GPU cgroup controller

[Michal Koutný]

Hello.

On Wed, Mar 09, 2022 at 04:52:11PM +0000, "T.J. Mercier" <tjmercier at google.com> wrote:
> +The new cgroup controller would:
> +
> +* Allow setting per-cgroup limits on the total size of buffers charged to it.

What is the meaning of the total? (I only have very naïve
understanding of the device buffers.)

Is it like a) there's global pool of memory that is partitioned among
individual devices or b) each device has its own specific type of memory
and adding across two devices is adding apples and oranges or c) there
can be various devices both of a) and b) type?

(Apologies not replying to previous versions and possibly missing
anything.)

Thanks,
Michal