Our research group is more interested in system virtualization since we would like to see networks go beyond providing connectivity and QoS on that connectivity. It is true that there are many end-host virtualization ideas led by other forums and data-center experts. But still, it would be more interesting for our group to participate in a research activity that would include the virtualization of (maybe limited to in network) storage and processing besides forwarding. We need coherent mechanisms for resource identification, allocation, monitoring, and management over wide-area networks. We also need mechanisms that can describe the degree of virtualization (e.g., what is the isolation model for different resources at different autonomous networks). Ulas On Thu, Oct 15, 2009 at 9:14 AM, James Kempf <james.kempf at ericsson.com> wrote: > Hi Rob, > > I guess FlowVisor could rewrite the OpenFlow protocol coming from the virtualized controllers to insert LAN QoS, right? That would enforce isolation for Enterprise GENI. > > I was mainly thinking about the WAN case. My understanding from a discussion in the PlanetLab GENI meeting in Seattle is that the plan was to use IP overlays between Enterprise GENI networks. > > jak > >> -----Original Message----- >> From: rob.sherwood at gmail.com [mailto:rob.sherwood at gmail.com] >> On Behalf Of Rob Sherwood >> Sent: Thursday, October 15, 2009 8:47 AM >> To: James Kempf >> Cc: Thomas Narten; Joe Touch; nvrg at listserv.gwdg.de >> Subject: Re: [nvrg-bof] poll on charter focus - RESPONSES DUE OCT 23 >> >> My preference is for the group to concentrate on network >> rather than systems virtualization, but I also definitely >> agree with Thomas. >> >> On Mon, Oct 12, 2009 at 8:15 AM, James Kempf >> <james.kempf at ericsson.com> wrote: >> > Another topic is "over the top" v.s. "close to the metal" >> network virtualization. Talking to GENI researchers, they >> seem to be planning to run virtualized networks as overlays >> like X-Bone was. This is in contrast to the, shall we say, >> "original promise" of virtualized networks, which is that >> they provide isolation between traffic on different "slices". >> Providing isolation while still providing the cost benefits >> of statistical multiplexing, especially across service >> providers, is a challenging research problem. Most L2 VPNs >> with service guarantees are expensive and time consuming to >> provision and confined to a single provider, which is >> probably why academic researchers aren't planning on using >> them. And statistical multiplexing is not possible because >> the VPN customers ping constantly to make sure they are >> getting their SLAs fufilled. >> >> Fwiw, I'm working in GENI with my FlowVisor virtualization >> layer project (tech report newly available at >> http://www.openflowswitch.org/wk/index.php/FlowVisor if >> anyone is interested), and while I'm not sure where you draw >> the line between "over the top" vs. "close to the metal", >> FlowVisor (intuitively to me at least) would seem to run >> close to the metal and is not really an overlay like X-Bone. >> >> Cheers, >> >> - Rob >> . >>
Note Well: Messages sent to this mailing list are the opinions of the senders and do not imply endorsement by the IETF.