From mboxrd@z Thu Jan 1 00:00:00 1970 From: Patrick McHardy Subject: Re: [PATCH net-next-2.6 v3] net_sched: SFB flow scheduler Date: Wed, 23 Feb 2011 17:20:20 +0100 Message-ID: <4D6533C4.6000601@trash.net> References: <20110221160306.GA9650@tuxdriver.com> <1298308283.2849.5.camel@edumazet-laptop> <1298390536.2861.9.camel@edumazet-laptop> <1298474091.3301.364.camel@edumazet-laptop> <20110223074305.755c5713@nehalam> <1298477600.3301.367.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Stephen Hemminger , David Miller , Juliusz Chroboczek , "John W. Linville" , netdev , Andi Kleen To: Eric Dumazet Return-path: Received: from stinky.trash.net ([213.144.137.162]:54921 "EHLO stinky.trash.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753920Ab1BWQUX (ORCPT ); Wed, 23 Feb 2011 11:20:23 -0500 In-Reply-To: <1298477600.3301.367.camel@edumazet-laptop> Sender: netdev-owner@vger.kernel.org List-ID: Am 23.02.2011 17:13, schrieb Eric Dumazet: > Le mercredi 23 f=C3=A9vrier 2011 =C3=A0 07:43 -0800, Stephen Hemminge= r a =C3=A9crit : >> On Wed, 23 Feb 2011 16:14:51 +0100 >> Eric Dumazet wrote: >> >>> 1) SFB default child qdisc is pfifo_fast. It can be changed by anot= her >>> qdisc but a child qdisc MUST not drop a packet previously queued. T= his >>> is because SFB needs to handle a dequeued packet in order to mainta= in >>> its virtual queue states. pfifo_head_drop or CHOKe should not be us= ed. >> >> Why not add a flag field to Qdisc_ops and to mark qdisc's that >> are (or not) work conserving? >> >=20 > That was my initial idea, but have no idea how to implement it (outsi= de > of fast path, I mean...) This also doesn't really have anything to do with work-conserving qdiscs, SFB f.i. is work conserving, but still might drop other packets. Actually I don't think there's any qdisc besides the *fifos that can reasonably be used with SFB, so we might as well only support a built-in qdisc.