From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [Bloat] shaper team forming up Date: Tue, 15 Mar 2011 15:51:51 -0700 (PDT) Message-ID: <20110315.155151.226785359.davem@davemloft.net> References: <5BC42741-852B-4699-BA5D-D70B8D610D96@gmail.com> <1300134277.2649.19.camel@edumazet-laptop> <1300164166.2649.70.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: Text/Plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: chromatix99@gmail.com, d@taht.net, netdev@vger.kernel.org To: eric.dumazet@gmail.com Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:38494 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752042Ab1COWvO convert rfc822-to-8bit (ORCPT ); Tue, 15 Mar 2011 18:51:14 -0400 In-Reply-To: <1300164166.2649.70.camel@edumazet-laptop> Sender: netdev-owner@vger.kernel.org List-ID: =46rom: Eric Dumazet Date: Tue, 15 Mar 2011 05:42:46 +0100 > Le lundi 14 mars 2011 =E0 21:24 +0100, Eric Dumazet a =E9crit : >=20 > David, it seems ip_tos2prio is wrong on its 2nd entry : Indeed, and in context, this is simply a thinko which has survived sinc= e ECN support first got added to the tree, here's the relevant hunk: -------------------- @@ -152,23 +152,29 @@ struct dst_ops ipv4_dst_ops =3D sizeof(struct rtable), }; =20 +#ifdef CONFIG_INET_ECN +#define ECN_OR_COST(class) TC_PRIO_##class +#else +#define ECN_OR_COST(class) TC_PRIO_FILLER +#endif + __u8 ip_tos2prio[16] =3D { TC_PRIO_BESTEFFORT, - TC_PRIO_FILLER, + ECN_OR_COST(FILLER), TC_PRIO_BESTEFFORT, - TC_PRIO_FILLER, + ECN_OR_COST(BESTEFFORT), TC_PRIO_BULK, - TC_PRIO_FILLER, + ECN_OR_COST(BULK), TC_PRIO_BULK, - TC_PRIO_FILLER, + ECN_OR_COST(BULK), TC_PRIO_INTERACTIVE, - TC_PRIO_FILLER, + ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE, - TC_PRIO_FILLER, + ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE_BULK, - TC_PRIO_FILLER, + ECN_OR_COST(INTERACTIVE_BULK), TC_PRIO_INTERACTIVE_BULK, - TC_PRIO_FILLER + ECN_OR_COST(INTERACTIVE_BULK) };