From owner-freebsd-net  Fri Nov 30  9:58:32 2001
Delivered-To: freebsd-net@freebsd.org
Received: from khavrinen.lcs.mit.edu (khavrinen.lcs.mit.edu [18.24.4.193])
	by hub.freebsd.org (Postfix) with ESMTP id 3A15C37B419
	for <net@FreeBSD.ORG>; Fri, 30 Nov 2001 09:58:30 -0800 (PST)
Received: (from wollman@localhost)
	by khavrinen.lcs.mit.edu (8.11.4/8.11.4) id fAUHwSP28351;
	Fri, 30 Nov 2001 12:58:28 -0500 (EST)
	(envelope-from wollman)
Date: Fri, 30 Nov 2001 12:58:28 -0500 (EST)
From: Garrett Wollman <wollman@khavrinen.lcs.mit.edu>
Message-Id: <200111301758.fAUHwSP28351@khavrinen.lcs.mit.edu>
To: Jonathan Lemon <jlemon@flugsvamp.com>
Cc: net@FreeBSD.ORG
Subject: Re: TCP anomalies (was Re: FreeBSD performing worse than Linux?)
In-Reply-To: <200111300647.fAU6l9K60404@prism.flugsvamp.com>
References: <local.mail.freebsd-net/20011128102241.6887B380A@overcee.netplex.com.au>
	<local.mail.freebsd-net/20011128112006.195983808@overcee.netplex.com.au>
	<local.mail.freebsd-net/20011129105321.C74413@monorchid.lemis.com>
	<local.mail.freebsd-net/200111290113.fAT1DnH04474@khavrinen.lcs.mit.edu>
	<local.mail.freebsd-net/200111300518.fAU5IXx11078@c527597-a.cstvl1.sfba.home.com>
	<200111300647.fAU6l9K60404@prism.flugsvamp.com>
Sender: owner-freebsd-net@FreeBSD.ORG
Precedence: bulk
List-ID: <freebsd-net.FreeBSD.ORG>
List-Archive: <http://docs.freebsd.org/mail/> (Web Archive)
List-Help: <mailto:majordomo@FreeBSD.ORG?subject=help> (List Instructions)
List-Subscribe: <mailto:majordomo@FreeBSD.ORG?subject=subscribe%20freebsd-net>
List-Unsubscribe: <mailto:majordomo@FreeBSD.ORG?subject=unsubscribe%20freebsd-net>
X-Loop: FreeBSD.org

<<On Fri, 30 Nov 2001 00:47:09 -0600 (CST), Jonathan Lemon <jlemon@flugsvamp.com> said:

[Quoting Bruce Mah:]

>> happens.  In *most* cases, the receiver somehow gets the missing data
>> because you can later see it acking later sequence numbers.  The first
>> place I saw this was at :41.504152.

Those are not duplicate acks because the window is still getting updated.

>> Another place to look is the large number of consecutive dupacks
>> starting around :41.978767.  I don't know what's happening here, but
>> after a long time (about a second?!?) the sender finally gives up and
>> sends the receiver what it wants.

> Yes, I think that area (I was looking at it too) provides a fairly
> good illustration that fast retransmits are broken.  The transmit 
> at 14:01:42.969338 appears to be the retransmit timer finally kicking in.

Yes, that's the conclusion Tim Shepard and I came to as well.

-GAWollman


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-net" in the body of the message