Thread (1 message) 1 message, 1 author, 2007-06-05

RE: [Xen-devel] [PATCH RFC 1/3] virtio infrastructure

From: Rusty Russell <hidden>
Date: 2007-06-05 02:27:08

On Tue, 2007-06-05 at 02:05 +0000, Santos, Jose Renato G wrote:
quoted
From: Jeremy Fitzhardinge [mailto:jeremy@goop.org] 
The hope is that the Xen-specific elements of the driver will 
be restricted to Xen-specific things like grant tables, and 
the bulk of the driver and its logic can be common.  Whether 
that can be achieved and still retain the full 
performance/features of the entirely Xen-specific netfront 
driver remains to be seen.  I haven't had a chance to look at 
doing any Xen-virtio glue yet, so I'm not really sure how it 
will work out.

    J
  Ok, if you share some common code this could be beneficial, but
  in the specific case of Xen networking I believe most of netfront
  code is Xen specific.  I think that a generic "virtual-IO" layer 
  would not be beneficial in this case, but instead it would 
  only add extra complexity to glue the layers.
This is precisely the plan: to code it up and look hard at it.  If
performance gets hurt, it's a lose.  If performance is equal and the
code is clearer, it's a win, and this is my goal.

Perhaps you underestimate how much of the Xen netfront driver is
actually dealing with things which *any* efficient virtio I/O netdriver
will have to wrestle with.

Thanks!
Rusty.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help