Re: Window Scale option
Matt Mathis <mathis@psc.edu> Tue, 05 May 1998 18:56 UTC
Delivery-Date: Tue, 05 May 1998 14:56:39 -0400
Return-Path: tcplw-relay@services.BSDI.COM
Received: from cnri.reston.va.us (ns.cnri.reston.va.us [132.151.1.1]) by ietf.org (8.8.5/8.8.7a) with ESMTP id OAA12112 for <ietf-archive@ietf.org>; Tue, 5 May 1998 14:56:38 -0400 (EDT)
Received: from services.BSDI.COM (services.BSDI.COM [205.230.225.19]) by cnri.reston.va.us (8.8.5/8.8.7a) with ESMTP id OAA09331 for <IETF-archive@cnri.reston.va.us>; Tue, 5 May 1998 14:59:05 -0400 (EDT)
Received: (from daemon@localhost) by services.BSDI.COM (8.8.7/8.8.8) id MAA07075 for tcplw-list@bsdi.com; Tue, 5 May 1998 12:54:04 -0600 (MDT)
Received: from mailfilter.bsdi.com (mailfilter.BSDI.COM [205.230.225.21]) by services.BSDI.COM (8.8.7/8.8.8) with ESMTP id MAA07072 for <tcplw@bsdi.com>; Tue, 5 May 1998 12:54:03 -0600 (MDT)
Received: from zippy.psc.edu (zippy.psc.edu [128.182.61.149]) by mailfilter.bsdi.com (BSDI-MF 1.0) with ESMTP id MAA27907 for <tcplw@bsdi.com> env-from (mathis@psc.edu); Tue, 5 May 1998 12:52:52 -0600 (MDT)
Received: (from mathis@localhost) by zippy.psc.edu (8.8.5/8.8.2) id OAA09661; Tue, 5 May 1998 14:53:47 -0400 (EDT)
To: tcplw@bsdi.com
Subject: Re: Window Scale option
References: <199805042134.OAA05330@gecko.nas.nasa.gov>
From: Matt Mathis <mathis@psc.edu>
Date: Tue, 05 May 1998 14:53:46 -0400
In-Reply-To: "Kevin M. Lahey"'s message of Mon, 04 May 1998 14:34:50 -0700
Message-ID: <9jaf8wk0qt.fsf@zippy.psc.edu>
Lines: 41
X-Mailer: Gnus v5.3/Emacs 19.34
The SYN only restriction is far more problematic for the timestamp option than it is for than the window scale option. For example, if you have a laptop with a radio modem and a 100bT interface, you are likely to find that you are either wasting the skinny link with uncompressible timestamps, or underfilling the LAN because you didn't negotiate timestamps. Although you could implement per-route or per-interface flags to control TCPLW features, the real problem is the pervasive 1323 mindset that new options must never appear after the SYN-ACK. If this mindset is relaxed, I believe it is a 1 line code change to allow timestamps to be turned on at any point. Thus all TCP connections could start without timestamps, and once they enter a regime where timestamps help (due to either PAWS or RTTM) timestamps could be turned on. Unfortunately, RFC1323 is structured such that relaxing this specification requires almost a complete rewrite. I tried it at one point, and had to abandon the project. Is this worth revisiting? About window scale option: The cost of negotiating an excessive window shift is very small - it increases the quantization in the flow control for applications which are receiver limited. This might be an issue to an application that *depends* on being able to advance (or control) the window in tiny increments, but I know of none. In our autotuning TCP the window shift defaults to the smallest value needed to support the largest socket buffer allowed on the system. (As specified by sb_max on most systems). The actual receiver window can then default to some small value, to be updated by the application or other mechanisms as needed. See ftp://ftp.psc.edu/pub/networking/papers/autotune_sigcomm98.ps Thanks, --MM--
- Window Scale option David Borman
- Re: Window Scale option braden
- Re: Window Scale option David Borman
- Re: Window Scale option Kevin M. Lahey
- Re: Window Scale option David Borman
- Re: Window Scale option Kacheong Poon
- Re: Window Scale option braden
- Re: Window Scale option braden
- Re: Window Scale option Jason Thorpe
- Re: Window Scale option Kevin M. Lahey
- Re: Window Scale option Matt Mathis
- Re: Window Scale option braden
- Re: Window Scale option Matt Mathis
- Re: Window Scale option braden
- Re: Window Scale option braden
- Re: Window Scale option Jason Thorpe
- Re: Window Scale option braden
- Re: Window Scale option Matt Mathis
- Window Scale option -- what about null windows ? Christian Huitema