On Wed, Dec 31, 2008 at 6:36 PM, Christopher Morrow <[email protected]> wrote: >> Sure I can. My $2k COTS PC can route 500mbps easily. Packet switching > > sorry, of course you can make the assumption, I just don't think it > follows as closely to reality as you'd want. that 500mbps isn't doing > anything tough, with a small table, few interfaces, no services, no > acls/filtering/qos ... consumer PC's just aren't a good correlary for > backbone devices.
Hi Chris, My hypothetical $2k PC is grounded in the recent NANOG discussion entitled "gigabit Linux routers." The original poster in that discussion specifically wanted to do BGP, filtering and shaping under Linux. The NANOG discussion concluded that such a construct would reasonably route between 700mbps and 1gbs on current hardware. It was criticized as being less user-friendly and still buggier than a purpose-built router. So, according to the Ops, my $2k PC is validly comparable to a modern core router at the 500mbps level, with plenty of headroom. >> If you can move packets across an interface at the given data rate >> then you can blindly multiplex and demultiplex packets from and to >> lower speed interfaces. This reduces the problem to one previously >> solved. There's doubtless a better solution but for conceptual >> purposes, that eliminates the data rate boundary condition as an >> active factor in the scalability assessment. > > at a gross level it might be comparable, but I'm not sure it > helps cost a device that'll fit in a half-rack and push 1600gbps > (T1600-juniper/ASR9k-cisco). I'm not looking for that cost. If I can demonstrate that there is an upper-bound cost for building a router whose cost varies linearly with the gbps pushed, without regard to the BGP table size then I can eliminate the router's gbps rate from the equation that describes the upper bound for processing BGP. This says nothing about the average case, in which I can build a cheaper router whose cost does vary with the BGP table size. But I don't need to find BGP's average case to calculate an upper bound. And I certainly don't need to find the average case to demonstrate that a calculable upper bound exists. Regards, Bill Herrin -- William D. Herrin ................ [email protected] [email protected] 3005 Crane Dr. ...................... Web: <http://bill.herrin.us/> Falls Church, VA 22042-3004 _______________________________________________ rrg mailing list [email protected] https://www.irtf.org/mailman/listinfo/rrg
