Date: Sat, 26 Apr 1997 20:00:18 -0400 From: dennis <dennis@etinc.com> To: dg@root.com Cc: "Michael K. Sanders" <msanders@aros.net>, Christopher Sedore <cmsedore@mailbox.syr.edu>, freebsd-hackers@FreeBSD.ORG, isp@FreeBSD.ORG Subject: Re: Router statistics Message-ID: <3.0.32.19970426200011.00b9aad0@etinc.com>
next in thread | raw e-mail | index | archive | help
At 03:55 PM 4/26/97 -0700, David Greenman wrote: >>Now I assume that this machine has a rather heavy overhead with all of the >>users >>and disk activity....do you have any estimates of the impact of this on the >>overall >>networking throughput? Obviously the SCSI activity is going to suck up much >>bus bandwidth..... > > The numbers are packet sends/receives to user processes throught the >TCP/IP stack. I would expect the packet forwording capability to be much >greater. The majority of the CPU time is spent doing file related things, >not networking. > >>As for the Intel Pro/100B ...is this a 10/100MB device? Does it have separate >>TP connectors, or 1? Are there any clones that are supported, or any versions >>of it that are not supported? > > 10/100, one connection, one vendor. The one vendor is a good thing, >however, because the design isn't "pot luck" and the device driver is >much less complicated as well. Or in other words, good for users, bad >for Intel haters. The chip is available from Intel for people if they >want to make clone cards, however. Thats good....and I've seen them for $139. (a good price?), which isn't bad at all. I did notice that its a rather long card, which may be an issue..... Dennis > >-DG > >David Greenman >Core-team/Principal Architect, The FreeBSD Project > > >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3.0.32.19970426200011.00b9aad0>