From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756065AbYIJWMQ (ORCPT ); Wed, 10 Sep 2008 18:12:16 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754245AbYIJWLs (ORCPT ); Wed, 10 Sep 2008 18:11:48 -0400 Received: from postel.suug.ch ([194.88.212.233]:43395 "EHLO postel.suug.ch" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754068AbYIJWLr (ORCPT ); Wed, 10 Sep 2008 18:11:47 -0400 Date: Thu, 11 Sep 2008 00:12:06 +0200 From: Thomas Graf To: Ranjit Manomohan Cc: David Miller , kaber@trash.net, akpm@linux-foundation.org, lizf@cn.fujitsu.com, menage@google.com, linux-kernel@vger.kernel.org, netdev@vger.kernel.org Subject: Re: [PATCH 0/2] Traffic control cgroups subsystem Message-ID: <20080910221206.GI20815@postel.suug.ch> References: <20080910.132251.73509521.davem@davemloft.net> <166fe7950809101344l7a5e2b7pfba8b2a7c03814a1@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <166fe7950809101344l7a5e2b7pfba8b2a7c03814a1@mail.gmail.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Ranjit Manomohan 2008-09-10 13:44 > On Wed, Sep 10, 2008 at 1:22 PM, David Miller wrote: > > > > I definitely prefer Thomas Graf's work, this stuff is very ugly > > and way overengineered. > > > > Could you be more specific? Thomas' work is almost identical to this > (except that he does not store the cgroup id into the socket which is > a trivial change which has downsides which I have pointed out). > > Additionally this approach has only minor modifications to the core > networking stack. What portions do you consider ugly and over > engineered and what alternative implementations would you prefer? > Please see the follow up I have sent to Thomas' proposal about why we > need this design approach to handle the inbound case. WRT the inbound case, after some experiments I decided to dismiss the ingress case at all and stick to something as simple as possible for egress. The reason for this is that it is a very expensive operation to associate a packet with a task on classifier level. Taking this cost, it does not add up with the very limited capabilities of ingress shaping. Ingress shaping is best effort at best. It works fairly well with a very limited number of bulk data streams but usualy fails miserably in common congestion situations where a cgroup classifier would be useful. > I'd be ok if you accepted either change since we just want a standard > kernel mechanism to do this. Agreed. I think your approach is very reasonable but considering the reasons I've given above and in the other thread I found it could be done in a more simple and direct way.