Re: [PATCH-for-9.1 v2 2/3] migration: Remove RDMA protocol handling

[Peter Xu <peterx@redhat.com>]

On Wed, May 01, 2024 at 04:59:38PM +0100, Daniel P. Berrangé wrote:
> On Wed, May 01, 2024 at 11:31:13AM -0400, Peter Xu wrote:
> > What I worry more is whether this is really what we want to keep rdma in
> > qemu, and that's also why I was trying to request for some serious
> > performance measurements comparing rdma v.s. nics.  And here when I said
> > "we" I mean both QEMU community and any company that will support keeping
> > rdma around.
> > 
> > The problem is if NICs now are fast enough to perform at least equally
> > against rdma, and if it has a lower cost of overall maintenance, does it
> > mean that rdma migration will only be used by whoever wants to keep them in
> > the products and existed already?  In that case we should simply ask new
> > users to stick with tcp, and rdma users should only drop but not increase.
> > 
> > It seems also destined that most new migration features will not support
> > rdma: see how much we drop old features in migration now (which rdma
> > _might_ still leverage, but maybe not), and how much we add mostly multifd
> > relevant which will probably not apply to rdma at all.  So in general what
> > I am worrying is a both-loss condition, if the company might be easier to
> > either stick with an old qemu (depending on whether other new features are
> > requested to be used besides RDMA alone), or do periodic rebase with RDMA
> > downstream only.
> 
> I don't know much about the originals of RDMA support in QEMU and why
> this particular design was taken. It is indeed a huge maint burden to
> have a completely different code flow for RDMA with 4000+ lines of
> custom protocol signalling which is barely understandable.
> 
> I would note that /usr/include/rdma/rsocket.h provides a higher level
> API that is a 1-1 match of the normal kernel 'sockets' API. If we had
> leveraged that, then QIOChannelSocket class and the QAPI SocketAddress
> type could almost[1] trivially have supported RDMA. There would have
> been almost no RDMA code required in the migration subsystem, and all
> the modern features like compression, multifd, post-copy, etc would
> "just work".
> 
> I guess the 'rsocket.h' shim may well limit some of the possible
> performance gains, but it might still have been a better tradeoff
> to have not quite so good peak performance, but with massively
> less maint burden.

My understanding so far is RDMA is sololy for performance but nothing else,
then it's a question on whether rdma existing users would like to do so if
it will run slower.

Jinpu mentioned on the explicit usages of ib verbs but I am just mostly
quotting that word as I don't really know such details:

https://lore.kernel.org/qemu-devel/CAMGffEm2TWJxOPcNQTQ1Sjytf5395dBzTCMYiKRqfxDzJwSN6A@mail.gmail.com/

So not sure whether that applies here too, in that having qiochannel
wrapper may not allow direct access to those ib verbs.

Thanks,

> 
> With regards,
> Daniel
> 
> [1] "almost" trivially, because the poll() integration for rsockets
>     requires a bit more magic sauce since rsockets FDs are not
>     really FDs from the kernel's POV. Still, QIOCHannel likely can
>     abstract that probme.
> -- 
> |: https://berrange.com      -o-    https://www.flickr.com/photos/dberrange :|
> |: https://libvirt.org         -o-            https://fstop138.berrange.com :|
> |: https://entangle-photo.org    -o-    https://www.instagram.com/dberrange :|
> 

-- 
Peter Xu