From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757241AbYHPAFL (ORCPT ); Fri, 15 Aug 2008 20:05:11 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752086AbYHPAE6 (ORCPT ); Fri, 15 Aug 2008 20:04:58 -0400 Received: from 197.Red-80-32-81.staticIP.rima-tde.net ([80.32.81.197]:51214 "EHLO mail.pina.cat" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750922AbYHPAE6 (ORCPT ); Fri, 15 Aug 2008 20:04:58 -0400 Date: Sat, 16 Aug 2008 01:44:02 +0200 From: Carles Pina i Estany To: linux-kernel@vger.kernel.org Subject: network accounting by process Message-ID: <20080815234402.GA8445@pina.cat> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hello, Recently I've discovered the IO Accounting (I mean, /proc/PID/io). It's very interesting, specially together with iotop (thanks!) I wonder: is there something in the proc fs similar for network? How much bytes the _process_ are receiving/sending just now? I've checked and I haven't found. If there isn't any wat to get this information: is there any technical problem to not have it? It looks like it would be possible to add something similar in ipv4 level (net/ipv4/af_inet.c for example). Thank you, -- Carles Pina i Estany GPG id: 0x17756391 http://pinux.info