From owner-freebsd-net@FreeBSD.ORG  Fri Jan 20 12:00:36 2006
Return-Path: <owner-freebsd-net@FreeBSD.ORG>
X-Original-To: freebsd-net@freebsd.org
Delivered-To: freebsd-net@freebsd.org
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id E478116A422
	for <freebsd-net@freebsd.org>; Fri, 20 Jan 2006 12:00:36 +0000 (GMT)
	(envelope-from dclerc55@hotmail.com)
Received: from hotmail.com (bay112-f17.bay112.hotmail.com [64.4.26.27])
	by mx1.FreeBSD.org (Postfix) with ESMTP id BC28B43D4C
	for <freebsd-net@freebsd.org>; Fri, 20 Jan 2006 12:00:35 +0000 (GMT)
	(envelope-from dclerc55@hotmail.com)
Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC;
	Fri, 20 Jan 2006 04:00:35 -0800
Message-ID: <BAY112-F17BB7816B2822134EE27A0D01F0@phx.gbl>
Received: from 64.4.26.200 by by112fd.bay112.hotmail.msn.com with HTTP;
	Fri, 20 Jan 2006 12:00:35 GMT
X-Originating-IP: [24.120.192.133]
X-Originating-Email: [dclerc55@hotmail.com]
X-Sender: dclerc55@hotmail.com
From: "David Clerc" <dclerc55@hotmail.com>
To: freebsd-net@freebsd.org
Date: Fri, 20 Jan 2006 13:00:35 +0100
Mime-Version: 1.0
Content-Type: text/plain; format=flowed
X-OriginalArrivalTime: 20 Jan 2006 12:00:35.0061 (UTC)
	FILETIME=[1EDD4250:01C61DB9]
Subject: RFC 3042 support in FreeBSD 6
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: Networking and TCP/IP with FreeBSD <freebsd-net.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-net>,
	<mailto:freebsd-net-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-net>
List-Post: <mailto:freebsd-net@freebsd.org>
List-Help: <mailto:freebsd-net-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-net>,
	<mailto:freebsd-net-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Fri, 20 Jan 2006 12:00:37 -0000

Hi,

I have a remark about the RFC 3042 code that is implemented in
tcp_input.c (CVS version 1.281.2.2). When a duplicate ack comes in, the
code saves the congestion window (cwnd), changes it to allow one packet
to be sent, and then calls tcp_output().

Is there a reason for not saving the bandwidth window (bwnd), and
changing it to the same value as cwnd ? I have a case (half duplex
link), where the bwnd is at its lowest value (6144), preventing the
limited transmit to occur (i.e. tcp_output does not send any packet
because bwnd forces sendwin to a value that is lower than cwnd).

David

_________________________________________________________________
Don't just search. Find. Check out the new MSN Search! 
http://search.msn.click-url.com/go/onm00200636ave/direct/01/