nanog mailing list archives
Re: Core router bakeoff?
From: "Perry E. Metzger" <perry () piermont com>
Date: Fri, 08 May 1998 09:33:46 -0400
Tony Li writes:
BTW, NetBSD with the recent flow cache mods can handle at least 150,000 packets per second. We haven't seen what the actual upper limit is, but that number doesn't seem to be eating a lot of CPU.Interesting. Have you done any scalability testing? Per-flow state has been shown to scale poorly in Internet backbones.
I agree with you that it doesn't scale well to huge routers. I am certain that it would work very badly in MCI's backbone. It probably will work just fine in a small provider, though, and those are most of the guys who want to roll their own out of PCs anyway. If you want to pump half a gigabit through on a giant peering router, caches will lose, and the only thing that will do you right is real router hardware. Perry
Current thread:
- Core router bakeoff? Rob M VanHooren (May 07)
- Re: Core router bakeoff? Perry E. Metzger (May 07)
- Re: Core router bakeoff? Karl Denninger (May 07)
- Re: Core router bakeoff? Perry E. Metzger (May 07)
- Re: Core router bakeoff? Tony Li (May 08)
- Re: Core router bakeoff? Paul Vixie (May 08)
- Re: Core router bakeoff? Neil J. McRae (May 08)
- Re: Core router bakeoff? Paul A Vixie (May 08)
- Re: Core router bakeoff? Tony Li (May 08)
- Re: Core router bakeoff? Karl Denninger (May 07)
- Re: Core router bakeoff? Perry E. Metzger (May 08)
- Re: Core router bakeoff? Tony Li (May 08)
- Re: Core router bakeoff? Perry E. Metzger (May 07)
- Re: Core router bakeoff? Michael H. Lambert (May 08)
- Re: Core router bakeoff? Al Reuben (May 08)
- Re: Core router bakeoff? Jason L. Weisberger (May 08)
- Re: Core router bakeoff? Jason L. Weisberger (May 07)
- Re: Core router bakeoff? J.D. Falk (May 07)
- Re: Core router bakeoff? Perry E. Metzger (May 07)
- Re: Core router bakeoff? Andrew Bangs (May 07)