From mboxrd@z Thu Jan 1 00:00:00 1970 From: James Morris Subject: Re: [RFC] [patch 5/6] [Network namespace] ipv4 isolation Date: Fri, 9 Jun 2006 20:23:39 -0400 (EDT) Message-ID: References: <20060609210202.215291000@localhost.localdomain> <20060609210631.346330000@localhost.localdomain> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: linux-kernel@vger.kernel.org, netdev@vger.kernel.org, serue@us.ibm.com, haveblue@us.ibm.com, clg@fr.ibm.com Return-path: Received: from mail1.sea5.speakeasy.net ([69.17.117.3]:19398 "EHLO mail1.sea5.speakeasy.net") by vger.kernel.org with ESMTP id S932601AbWFJAXn (ORCPT ); Fri, 9 Jun 2006 20:23:43 -0400 To: dlezcano@fr.ibm.com In-Reply-To: <20060609210631.346330000@localhost.localdomain> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Fri, 9 Jun 2006, dlezcano@fr.ibm.com wrote: > When an outgoing packet has the loopback destination addres, the > skbuff is filled with the network namespace. So the loopback packets > never go outside the namespace. This approach facilitate the migration > of loopback because identification is done by network namespace and > not by address. The loopback has been benchmarked by tbench and the > overhead is roughly 1.5 % I think you'll need to make it so this code has zero impact when not configured. - James -- James Morris