From owner-freebsd-net@FreeBSD.ORG Fri Jun 14 10:07:46 2013 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [8.8.178.115]) by hub.freebsd.org (Postfix) with ESMTP id 1665DC12; Fri, 14 Jun 2013 10:07:46 +0000 (UTC) (envelope-from glebius@FreeBSD.org) Received: from cell.glebius.int.ru (glebius.int.ru [81.19.69.10]) by mx1.freebsd.org (Postfix) with ESMTP id 979C91471; Fri, 14 Jun 2013 10:07:45 +0000 (UTC) Received: from cell.glebius.int.ru (localhost [127.0.0.1]) by cell.glebius.int.ru (8.14.7/8.14.7) with ESMTP id r5EA7iUR028352; Fri, 14 Jun 2013 14:07:44 +0400 (MSK) (envelope-from glebius@FreeBSD.org) Received: (from glebius@localhost) by cell.glebius.int.ru (8.14.7/8.14.7/Submit) id r5EA7ir1028351; Fri, 14 Jun 2013 14:07:44 +0400 (MSK) (envelope-from glebius@FreeBSD.org) X-Authentication-Warning: cell.glebius.int.ru: glebius set sender to glebius@FreeBSD.org using -f Date: Fri, 14 Jun 2013 14:07:44 +0400 From: Gleb Smirnoff To: Luigi Rizzo Subject: Re: [PATH] ALTQ(9) codel algorithm implementation Message-ID: <20130614100744.GS12443@glebius.int.ru> References: <20130614095125.GQ12443@FreeBSD.org> <20130614100828.GA48119@onelab2.iet.unipi.it> MIME-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Disposition: inline In-Reply-To: <20130614100828.GA48119@onelab2.iet.unipi.it> User-Agent: Mutt/1.5.21 (2010-09-15) Cc: Ermal Lu?i , freebsd-net X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 14 Jun 2013 10:07:46 -0000 Luigi, On Fri, Jun 14, 2013 at 12:08:28PM +0200, Luigi Rizzo wrote: L> > I'm afraid we can't grow mbuf packet header with 8 bytes just to satisfy L> > the ALTQ codel algo, which would definitely have a limited usage among L> > FreeBSD users. Thus, "enqueue_time" should go into mbuf_tags(9) not into L> > mbuf packet header. L> L> not to take positions one way or the other, but getting and releasing L> a tag on every packet is going to kill performance. Does ALTQ care about performance? L> If i remember well, 2-3 years ago at bsdcan there was discussion L> (and mention of some pending work, jeffr maybe ?) L> on providing some leading space in the mbuf so one could put there L> tags (e.g. ipfw and dummynet ones) without having to allocate them. L> Not sure where is this. I even tried to prototype that. -- Totus tuus, Glebius.