Date: Mon, 30 Mar 1998 14:22:51 -0500 (EST) From: "Ron G. Minnich" <rminnich@Sarnoff.COM> To: Chris Csanady <ccsanady@friley585.res.iastate.edu> Cc: freebsd-hackers@FreeBSD.ORG Subject: Re: Virtual Interface Architecture Message-ID: <Pine.SUN.3.91.980330141830.4075F-100000@terra> In-Reply-To: <199803301840.MAA03732@friley585.res.iastate.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
http://www.extremelinux.org/activities/wkshop01/presentations/via/, also contact is pbozeman@lbl.gov pat's code does have some unet bits and pieces i understand. But it works and works well. word is that gigabit ethernet frames grow to 9300 bytes soon. Of course that will have interesting impacts on systems, with pci transactions of about 2048 cycles. Could be fun. > That should be good. :) I was under the impression that you could just > write a custom MCP to provide for VIA though, and get the same results. I assume MCP here is the myrinet code. This has been tried, but the numbers I saw were not that great. Unet is not dead. I think unet should be tried by "someone" on freebsd. We actually put an entire separate switched ethernet onto our latest cluster here for things like unet, hoping ... btw, a question for hackers: how hard would it be to get 10 microseconds latency on the tcp stack as it stands? Yes, i know: "impossible". how impossible? ron To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.SUN.3.91.980330141830.4075F-100000>