From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <sesse@samfundet.no>
Received: from cassarossa.samfundet.no (cassarossa.samfundet.no
	[IPv6:2001:67c:29f4::29])
	(using TLSv1 with cipher AES256-SHA (256/256 bits))
	(Client did not present a certificate)
	by huchra.bufferbloat.net (Postfix) with ESMTPS id 54A4421F1CF
	for <bloat@lists.bufferbloat.net>; Thu, 30 May 2013 02:53:08 -0700 (PDT)
Received: from pannekake.samfundet.no ([2001:67c:29f4::50] ident=unknown)
	by cassarossa.samfundet.no with esmtps
	(TLS1.0:DHE_RSA_AES_128_CBC_SHA1:16) (Exim 4.72)
	(envelope-from <sesse@samfundet.no>)
	id 1UhzXS-0000xw-DR; Thu, 30 May 2013 11:52:54 +0200
Received: from sesse by pannekake.samfundet.no with local (Exim 4.80)
	(envelope-from <sesse@samfundet.no>)
	id 1UhzXR-0004P5-8z; Thu, 30 May 2013 11:52:53 +0200
Date: Thu, 30 May 2013 11:52:53 +0200
From: "Steinar H. Gunderson" <sgunderson@bigfoot.com>
To: Jesper Dangaard Brouer <jbrouer@redhat.com>
Message-ID: <20130530095253.GA8461@uio.no>
References: <20130529151330.22c5c89e@redhat.com>
	<1369842724.5109.44.camel@edumazet-glaptop>
	<20130529155034.334092c5@nehalam.linuxnetplumber.net>
	<1369869506.5109.87.camel@edumazet-glaptop>
	<20130530111547.07397287@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20130530111547.07397287@redhat.com>
X-Operating-System: Linux 3.9.0+sesse01 on a x86_64
User-Agent: Mutt/1.5.21 (2010-09-15)
Cc: Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= <toke@toke.dk>,
	Mike Frysinger <vapier@gentoo.org>,
	Jiri Pirko <jpirko@redhat.com>, netdev@vger.kernel.org,
	Jiri Benc <jbenc@redhat.com>, Steven Barth <cyrus@openwrt.org>,
	"russell-tcatm@stuart.id.au" <russell-tcatm@stuart.id.au>,
	bloat@lists.bufferbloat.net, David Miller <davem@redhat.com>,
	Jussi Kivilinna <jussi.kivilinna@mbnet.fi>,
	Michal Soltys <soltys@ziu.info>,
	Patrick McHardy <kaber@trash.net>, Felix Fietkau <nbd@nbd.name>
Subject: Re: [Bloat] tc linklayer ADSL calc broken after commit 56b765b79
 (htb: improved accuracy at high rates)
X-BeenThere: bloat@lists.bufferbloat.net
X-Mailman-Version: 2.1.13
Precedence: list
List-Id: General list for discussing Bufferbloat <bloat.lists.bufferbloat.net>
List-Unsubscribe: <https://lists.bufferbloat.net/options/bloat>,
	<mailto:bloat-request@lists.bufferbloat.net?subject=unsubscribe>
List-Archive: <https://lists.bufferbloat.net/pipermail/bloat>
List-Post: <mailto:bloat@lists.bufferbloat.net>
List-Help: <mailto:bloat-request@lists.bufferbloat.net?subject=help>
List-Subscribe: <https://lists.bufferbloat.net/listinfo/bloat>,
	<mailto:bloat-request@lists.bufferbloat.net?subject=subscribe>
X-List-Received-Date: Thu, 30 May 2013 09:53:08 -0000

On Thu, May 30, 2013 at 11:15:47AM +0200, Jesper Dangaard Brouer wrote:
>  int pkt_len = skb->len + (encap_overhead * gso_segments);
>  int wire_sz = DIV_ROUND_UP(pkt_len,48)*53;
> 
> (I suspect, that the compiler might even optimize and remove any
> real divisions, I bet Eric can tell us.)

FWIW, GCC can change divisions by integer constants (even signed divisions)
to some multiplies and shifts, by way of some number theory magic.

/* Steinar */
-- 
Homepage: http://www.sesse.net/