From mboxrd@z Thu Jan 1 00:00:00 1970 From: Cong Wang Subject: Re: [PATCH net-next 0/2] handle_ing update Date: Mon, 11 May 2015 15:42:04 -0700 Message-ID: References: <20150510170550.GA4442@salvia> <20150511.110949.1369224056076525434.davem@davemloft.net> <55512BFD.3070400@plumgrid.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Cc: David Miller , Pablo Neira Ayuso , Daniel Borkmann , Jamal Hadi Salim , netdev To: Alexei Starovoitov Return-path: Received: from mail-wg0-f46.google.com ([74.125.82.46]:34913 "EHLO mail-wg0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751423AbbEKWmG (ORCPT ); Mon, 11 May 2015 18:42:06 -0400 Received: by wgbhc8 with SMTP id hc8so44138101wgb.2 for ; Mon, 11 May 2015 15:42:05 -0700 (PDT) In-Reply-To: <55512BFD.3070400@plumgrid.com> Sender: netdev-owner@vger.kernel.org List-ID: On Mon, May 11, 2015 at 3:23 PM, Alexei Starovoitov wrote: > On 5/11/15 3:03 PM, Cong Wang wrote: >> >> On Mon, May 11, 2015 at 8:09 AM, David Miller wrote: >>> >>> There is no difference between having ingress qdisc hanging off of >>> netdevice vs. the classifier list. They both serve the same purpose >>> and the change to use the classifier list merely removes one level >>> of indirection. >> >> >> With adding 8 bytes to each of the netdevice even when it doesn't >> have ingress qdisc attached at all... > > > we already said several times that the work is already on the way > to remove 'ingress_queue' from net_device. It will save much more > memory than addition of 8 bytes. This sounds like adding 8 bytes is a must step for removing more, I seriously doubt.