Date: Fri, 14 Jul 1995 19:05:52 +0930 (CST) From: Michael Smith <msmith@atrad.adelaide.edu.au> To: hackers@freebsd.org Subject: TCP Vegas/TCP lite patches... Message-ID: <199507140935.TAA15826@genesis.atrad.adelaide.edu.au>
next in thread | raw e-mail | index | archive | help
Terry Lambert stands accused of saying: > > There's a good paper on this out there by the X Kernel guys. They say > > the 4.4 networking code is significantly slower than the 4.3, and they > > tell why (and what to do about it). > > By popular and racous demand: > > ftp://ftp.cs.arizona.edu/xkernel/Papers/tcp_problems.ps Thanks for that, Terry; makes for interesting reading. The obvious question then is : Have these changes been implemented? If yes, neat! If not, is there any reason other than 'nobody dumb enough has stood up & done it?' If that's all, I'd be game to try it as soon as I can get the CTM megapatch to apply to my source tree (I suspect that coz I have 2.0.5 ALPHA it's not happy, but ctm simply stops with "exit(80)", which is puzzling... (there's no reference to '80' in the source, nor EAUTH, nor indeed 'exit'... ramble. I hope things will be better when I can dump the 2.0.5-RELEASE code off the CD). And to the second topic; the referenced paper talks about TCP Vegas, and sample code for same can be found at the same place, as well as another interesting paper discussing it at some length. I suspect that implementation of this may be beyond my khacking ability, (first look only) but again, if nobody else is game, I'll give it a try. -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] My car has "demand start" - Terry Lambert [[
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199507140935.TAA15826>