Hi Curtis, Scalability is not the only issue that DC operators concern. Energy conservation is also a critical issue. I wonder whether you are suggesting another "straw" by mentioning SDN. However, we do not intend to work on greening DCNs right now. In PANET-Problem Statement we scope our work in ISP networks.
Whatever the specific protocol is, only if it can be used to achieve our method then we can make use of it. The method is to aggregate traffic through protocol work and create opportunity for network devices to enter low power mode (e.g., sleeping) in order to achieve the energy conservation of the network. The apparent waste on idle power by high-end routers and switches makes us believe there is opportunity for this kind of energy saving. GreenTE is one of those solutions that reveal this feasibility. I feel that we are here trying to obtain conclusions based on guess rather than fact. Power saving of networks requires the cooperation of hardware & protocol. We need "walk on two legs". I think it's time to get more relevant observations along with hardware experts. Thanks, Mingui >-----Original Message----- >From: Curtis Villamizar [mailto:[email protected]] >Sent: Friday, March 29, 2013 5:01 AM >To: Mingui Zhang >Cc: Tony Tauber; Shane Amante; [email protected] >Subject: Re: I-D Action: draft-retana-rtgwg-eacp-01.txt > > >In message ><[email protected] >awei.com> >Mingui Zhang writes: >> >> >Now that you mention it, datacenter or campus LANs would appear to be the >> >biggest wins in terms of power and raw numbers of interfaces. >> >IEEE seems like a better match in that case. No idea if there are >> >things going >> >on in that venue. >> >> As for "datacenter or campus LANs", I'd mention that ISIS can be used >> as the control protocol (e.g., TRILL and SPB). This is an area that >> matches IETF. >> >> Mingui > > >Mingui, > >Are you familiar with the english (maybe just american) expression >"grabbing at straws"? > >I think datacenter interest in Trill and SPB is declining, >particularly in very large datacenters where scaling limits are being >felt. The current chaos in datacenters revolves around SDN, or more >precisely at this point, arguing about what SDN is and isn't. > >Curtis > > >> >-----Original Message----- >> >From: [email protected] [mailto:[email protected]] On Behalf >Of >> >Tony Tauber >> >Sent: Wednesday, March 27, 2013 9:15 AM >> >To: Shane Amante >> >Cc: [email protected] >> >Subject: Re: I-D Action: draft-retana-rtgwg-eacp-01.txt >> > >> >On Tue, Mar 26, 2013 at 12:05 PM, Shane Amante <[email protected]> >> >wrote: >> > >> > >> > >> > Thus, the only practical application I can see of power savings would >> > be on >> >copper interfaces at the deepest "edge" of the network, (U-PE to CE), but >> >there's no active routing protocols on those interfaces. And, although >there's >> >Layer-2 control protocols, e.g.: LLDP and the MEF's "Ethernet LMI", but I've >not >> >seen either of those achieve widespread deployment mostly because the CE >> >devices do not support it, (yet). But, we're the IETF, not the IEEE nor the >> >MEF ... so, I'm not clear what the IETF would be able to work on here. >> > >> > >> >Now that you mention it, datacenter or campus LANs would appear to be the >> >biggest wins in terms of power and raw numbers of interfaces. >> >IEEE seems like a better match in that case. No idea if there are things >going >> >on in that venue. >> > >> >Tony _______________________________________________ rtgwg mailing list [email protected] https://www.ietf.org/mailman/listinfo/rtgwg
