From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH v2 net-next-2.6] ifb: add performance flags Date: Mon, 03 Jan 2011 12:40:55 -0800 (PST) Message-ID: <20110103.124055.68142309.davem@davemloft.net> References: <20110103193703.GA1977@del.dom.local> <20110103.114033.28807428.davem@davemloft.net> <1294086922.2711.18.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: Text/Plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: jarkao2@gmail.com, xiaosuo@gmail.com, pstaszewski@itcare.pl, 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]:47584 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752930Ab1ACUkY convert rfc822-to-8bit (ORCPT ); Mon, 3 Jan 2011 15:40:24 -0500 In-Reply-To: <1294086922.2711.18.camel@edumazet-laptop> Sender: netdev-owner@vger.kernel.org List-ID: =46rom: Eric Dumazet Date: Mon, 03 Jan 2011 21:35:22 +0100 > Le lundi 03 janvier 2011 =E0 11:40 -0800, David Miller a =E9crit : >> I think at least TSO6 would very much be appropriate here. >=20 > Yes, why not, I am only wondering why loopback / dummy (and others ?) > only set NETIF_F_TSO :) TSO6 probably didn't exist when the current set were added, at least in the loopback case that's almost certainly the reason. > Since I want to play with ECN, I might also add NETIF_F_TSO_ECN ;) >=20 > For other flags, I really doubt it can matter on ifb ? >=20 > [PATCH v3 net-next-2.6] ifb: add performance flags >=20 > IFB can use the full set of features flags (NETIF_F_SG | > NETIF_F_FRAGLIST | NETIF_F_TSO | NETIF_F_NO_CSUM | NETIF_F_HIGHDMA) t= o > avoid unnecessary split of some packets (GRO for example) >=20 > Changli suggested to also set vlan_features, NETIF_F_TSO6, > NETIF_F_TSO_ECN. >=20 > Jarek suggested to add NETIF_F_HW_VLAN_TX as well. >=20 > Signed-off-by: Eric Dumazet I'll apply this, thanks Eric.