Re: [vnrg] FlowVisor : A Network Virtualization Layer

Hi Rob, Aaron,

We have agenda time available, but no webex yet. Plus I have a half-dead laptop (spontaneous crashes), which might handling this hard or tricky for me (unless somebody else takes over that part). 

Thanks,

  Martin

martin.stiemerling@neclab.eu

NEC Laboratories Europe - Network Research Division
NEC Europe Limited | Registered Office: NEC House, 1 Victoria Road, London W3 6BL | Registered in England 2832014 

> -----Original Message-----
> From: vnrg-bounces@irtf.org [mailto:vnrg-bounces@irtf.org] On Behalf Of
> Aaron Falk
> Sent: Tuesday, November 09, 2010 3:15 AM
> To: Rob Sherwood
> Cc: vnrg@irtf.org
> Subject: Re: [vnrg] FlowVisor : A Network Virtualization Layer
> 
> Hi Rob-
> 
> Glad to see you are on this list.  FYI, the research group meeting is
> scheduled for Friday 0900 - 1130 Beijing time.  Meetings are in general
> audiocast with jabber feedback channels so you are welcome to listen
> and participate if you'd like.  See
> http://www.ietf.org/meeting/79/remote-participation.html.  In fact,
> modulo the chairs' approval, I believe it is not too late to request
> agenda time for yourself and webex is available for remote
> presentation.
> 
> --aaron
> 
> On 11/9/10 1:00 AM, Rob Sherwood wrote:
> > Hello,
> >
> >
> > Apologies that I was not able to attend the working group meeting,
> but
> > thanks for the interest on FlowVisor.  I flipped through the slides
> at
> >
> > http://www.ietf.org/proceedings/79/slides/VNRG-0.pdf
> >
> > and at least from the slides (I'm not sure how the
> > presentation/discussion about these slides went) I think there might
> > be a few things that need clarification:
> >
> > In most of the flowvisor literature, we're very careful to describe
> > this as "network *slicing*" as opposed to "network virtualization".
> > The key differences (as brought out in the slides) is that current,
> > FlowVisor does not support:
> >
> > - two slices controlling the same virtual address space (e.g.,
> > 10.0.0.0/24) but the flowvisor rewriting them to different physical
> > addresses
> > - network topologies that are independent of the physical topology
> > (currently FlowVisor is restricted to subsets of the physical
> > topology)
> >
> > Both of these points are limits of the current implementation, but
> not
> > of the design, and my thoughts for the future are to take FV towards
> > implementing these points.
> >
> > If anyone is interested in learning more about FlowVisor or its
> > deployments as part of GENI, please let me know.
> >
> > Thanks again for the interest,
> >
> > - Rob
> > .
> >
> >
> >
> > On Sun, Nov 7, 2010 at 11:11 AM, Guillaume
> FORTAINE<gfortaine@live.com>  wrote:
> >> Hello,
> >> For your information :
> >> -Flowvisor :
> >> http://www.usenix.org/events/osdi/tech/slides/sherwood.pdf
> >> http://www.deutsche-telekom-laboratories.de/~robert/flowvisor-
> osdi10.pdf
> >> http://www.openflow.org/wk/index.php/FlowVisor
> >>
> >> Best Regards,
> >> Guillaume FORTAINE
> >>
> >> _______________________________________________
> >> vnrg mailing list
> >> vnrg@irtf.org
> >> https://www.irtf.org/mailman/listinfo/vnrg
> >>
> > _______________________________________________
> > vnrg mailing list
> > vnrg@irtf.org
> > https://www.irtf.org/mailman/listinfo/vnrg
> >
> _______________________________________________
> vnrg mailing list
> vnrg@irtf.org
> https://www.irtf.org/mailman/listinfo/vnrg