From owner-freebsd-ipfw@FreeBSD.ORG  Wed Mar 10 14:58:15 2010
Return-Path: <owner-freebsd-ipfw@FreeBSD.ORG>
Delivered-To: freebsd-ipfw@FreeBSD.ORG
Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34])
	by hub.freebsd.org (Postfix) with ESMTP id C41251065674
	for <freebsd-ipfw@FreeBSD.ORG>; Wed, 10 Mar 2010 14:58:15 +0000 (UTC)
	(envelope-from andrey.kropachev@gmail.com)
Received: from mx.kirovnet.ru (taurus.kirovnet.ru [92.39.64.230])
	by mx1.freebsd.org (Postfix) with ESMTP id 7DD238FC2D
	for <freebsd-ipfw@FreeBSD.ORG>; Wed, 10 Mar 2010 14:58:15 +0000 (UTC)
Received: from [192.168.2.68] by mx.kirovnet.ru with esmtp (Exim 4.69)
	(envelope-from <andrey.kropachev@gmail.com>) id 1NpMjQ-0001JG-C2
	for freebsd-ipfw@FreeBSD.ORG; Wed, 10 Mar 2010 17:17:53 +0300
Message-ID: <4B97AA08.6010102@gmail.com>
Date: Wed, 10 Mar 2010 17:17:44 +0300
From: Andrey Kropachev <andrey.kropachev@gmail.com>
User-Agent: Thunderbird 2.0.0.23 (X11/20090817)
MIME-Version: 1.0
To: freebsd-ipfw@FreeBSD.ORG
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Cc: 
Subject: Dummynet tuning
X-BeenThere: freebsd-ipfw@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
Reply-To: andrey.kropachev@gmail.com
List-Id: IPFW Technical Discussions <freebsd-ipfw.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-ipfw>,
	<mailto:freebsd-ipfw-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-ipfw>
List-Post: <mailto:freebsd-ipfw@freebsd.org>
List-Help: <mailto:freebsd-ipfw-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-ipfw>,
	<mailto:freebsd-ipfw-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Wed, 10 Mar 2010 14:58:15 -0000

Hi,

I'm trying to tune dummynet to shape a lot of traffic. I saw some 
opinions that the following patch will improve dummynet performance:
in /sys/netinet/ipfw/ip_dummynet.c

-#define        HASHSIZE        16
-#define        HASH(num)       ((((num) >> 8) ^ ((num) >> 4) ^ (num)) & 0x0f)
+#define        HASHSIZE        256
+#define        HASH(num)       ((((num) >> 8) ^ ((num) >> 4) ^ (num)) & 0xff)

The question is: will it increase dummynet performance? What will it 
actually do internally (luigi, question for you :) ?


Best regards,
Andrey Kropachev