From owner-freebsd-net@FreeBSD.ORG  Wed Jul 29 10:29:28 2009
Return-Path: <owner-freebsd-net@FreeBSD.ORG>
Delivered-To: freebsd-net@freebsd.org
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id 3C24C106566B
	for <freebsd-net@freebsd.org>; Wed, 29 Jul 2009 10:29:28 +0000 (UTC)
	(envelope-from ap00@mail.ru)
Received: from mx4.mail.ru (mx4.mail.ru [94.100.176.18])
	by mx1.freebsd.org (Postfix) with ESMTP id E30F98FC1A
	for <freebsd-net@freebsd.org>; Wed, 29 Jul 2009 10:29:27 +0000 (UTC)
	(envelope-from ap00@mail.ru)
Received: from mx48.mail.ru (mx48.mail.ru [94.100.176.62])
	by mx4.mail.ru (mPOP.Fallback_MX) with ESMTP id CDE518223E5
	for <freebsd-net@freebsd.org>; Wed, 29 Jul 2009 14:15:06 +0400 (MSD)
Received: from [91.190.115.253] (port=49549 helo=pstation)
	by mx48.mail.ru with asmtp id 1MW6BQ-000JWf-00
	for freebsd-net@freebsd.org; Wed, 29 Jul 2009 14:14:52 +0400
Date: Wed, 29 Jul 2009 14:17:08 +0400
From: Anthony Pankov <ap00@mail.ru>
X-Mailer: The Bat! (v1.51) Personal
X-Priority: 3 (Normal)
Message-ID: <98265976953.20090729141708@mail.ru>
To: freebsd-net@freebsd.org
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
X-Mras: Ok
Subject: TCP initial window size
X-BeenThere: freebsd-net@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
Reply-To: Anthony Pankov <ap00@mail.ru>
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: Wed, 29 Jul 2009 10:29:28 -0000


Can anybody explain me about initial TCP window sent to the client (in syn/ack packet),
please.

Is it unmanageable and always set to net.inet.tcp.recvspace?

(Due to use of syncache and syncache code is (tcp_syncache.c):
        /* Initial receive window: clip sbspace to [0 .. TCP_MAXWIN] */
        win = sbspace(&so->so_rcv);
        win = imax(win, 0);
        win = imin(win, TCP_MAXWIN);
        sc->sc_wnd = win;
)

If it is, then what bad things will happen if i replace code above by
code like this:

if (tcp_do_rfc3390)
  sc->sc_wnd = min(4*(sc->sc_peer_mss ? sc->sc_peer_mss:tcp_mssdflt ),
                   max(2 * (sc->sc_peer_mss ? sc->sc_peer_mss:tcp_mssdflt), 4380));
else
  sc->sc_wnd = (sc->sc_peer_mss ? sc->sc_peer_mss:tcp_mssdflt) * ss_fltsz;


Also, does local connection use syncache?


System: FreeBSD 6.2-RELEASE-p9

-- 
Best regards,
 Anthony                          mailto:ap00@mail.ru