[RFC] Make use of non-dynamic dmabuf in RDMA

Jason Gunthorpe jgg at nvidia.com
Wed Aug 25 12:18:32 UTC 2021


On Wed, Aug 25, 2021 at 08:17:51AM +0200, Christian König wrote:

> The only real option where you could do P2P with buffer pinning are those
> compute boards where we know that everything is always accessible to
> everybody and we will never need to migrate anything. But even then you want
> some mechanism like cgroups to take care of limiting this. Otherwise any
> runaway process can bring down your whole system.
 
Why? It is not the pin that is the problem, it was allocating GPU
dedicated memory in the first place. pinning it just changes the
sequence to free it. No different than CPU memory.

> Key question at least for me as GPU maintainer is if we are going to see
> modern compute boards together with old non-ODP setups. 

You should stop thinking about it as 'old non-ODP setups'.  ODP is
very much a special case that allows a narrow set of functionality to
work in a narrow situation. It has a high performance penalty and
narrow HW support.

So yes, compute boards are routinely used in scenarios where ODP is
not available, today and for the foreseeable future.

Jason


More information about the dri-devel mailing list