Re: [RFC PATCH 00/17] virtual-bus

[Gerd Hoffmann <kraxel@redhat.com>]

Avi Kivity wrote:
> There is no choice.  Exiting from the guest to the kernel to userspace
> is prohibitively expensive, you can't do that on every packet.

I didn't look at virtio-net very closely yet.  I wonder why the
notification is that a big issue though.  It is easy to keep the number
of notifications low without increasing latency:

Check shared ring status when stuffing a request.  If there are requests
not (yet) consumed by the other end there is no need to send a
notification.  That scheme can even span multiple rings (nics with rx
and tx for example).

Host backend can put a limit on the number of requests it takes out of
the queue at once.  i.e. block backend can take out some requests, throw
them at the block layer, check whenever any request in flight is done,
if so send back replies, start over again.  guest can put more requests
into the queue meanwhile without having to notify the host.  I've seen
the number of notifications going down to zero when running disk
benchmarks in the guest ;)

Of course that works best with one or more I/O threads, so the vcpu
doesn't has to stop running anyway to get the I/O work done ...

cheers,
  Gerd