From owner-freebsd-current Sun Jan 12 09:49:18 1997 Return-Path: Received: (from root@localhost) by freefall.freebsd.org (8.8.4/8.8.4) id JAA07327 for current-outgoing; Sun, 12 Jan 1997 09:49:18 -0800 (PST) Received: from halloran-eldar.lcs.mit.edu (halloran-eldar.lcs.mit.edu [18.26.0.159]) by freefall.freebsd.org (8.8.4/8.8.4) with SMTP id JAA07322 for ; Sun, 12 Jan 1997 09:49:15 -0800 (PST) Received: by halloran-eldar.lcs.mit.edu; (5.65v3.2/1.1.8.2/19Aug95-0530PM) id AA10630; Sun, 12 Jan 1997 12:49:10 -0500 Date: Sun, 12 Jan 1997 12:49:10 -0500 From: Garrett Wollman Message-Id: <9701121749.AA10630@halloran-eldar.lcs.mit.edu> To: Luigi Rizzo Cc: freebsd-current@FreeBSD.ORG Subject: TCP code (was Re: tcp_extenions=NO between to FreeBSD Hosts!?) In-Reply-To: <199701120904.KAA20383@labinfo.iet.unipi.it> References: <19970112060920.20637.qmail@mpress.com> <199701120904.KAA20383@labinfo.iet.unipi.it> Sender: owner-current@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk < said: > Maybe it's time to accept the idea that the TCP code is not carved on > stone. I for one would be more than willing to work on it. One of my long-term desires (parts of which you already see implemented in -current) is to get rid of all the socket-buffer nonsense in the TCP output path and do optimistic packet construction (and keep these verbatim in a separate retransmission queue). This should eventually result in a much, much cleaner TCP implementation which will have the additional benefit of running reasonably fast when the network is behaving well, and no worse than it does now when it is behaving badly. -GAWollman -- Garrett A. Wollman | O Siem / We are all family / O Siem / We're all the same wollman@lcs.mit.edu | O Siem / The fires of freedom Opinions not those of| Dance in the burning flame MIT, LCS, ANA, or NSA| - Susan Aglukark and Chad Irschick