From mboxrd@z Thu Jan 1 00:00:00 1970 From: Denys Fedoryschenko Subject: Re: bond + tc regression ? Date: Tue, 5 May 2009 19:25:50 +0300 Message-ID: <200905051925.50142.denys@visp.net.lb> References: <1241538358.27647.9.camel@hazard2.francoudi.com> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org To: Vladimir Ivashchenko Return-path: Received: from hosting.visp.net.lb ([194.146.153.11]:50752 "EHLO hosting.visp.net.lb" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752216AbZEEQZ4 (ORCPT ); Tue, 5 May 2009 12:25:56 -0400 In-Reply-To: <1241538358.27647.9.camel@hazard2.francoudi.com> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: Can you show example of rules you are putting? Probably i can find mistakes and give correct example and i will explain maybe why it is happened. On Tuesday 05 May 2009 18:45:58 Vladimir Ivashchenko wrote: > Hi, > > I have a traffic policing setup running on Linux, serving about 800 mbps > of traffic. Due to the traffic growth I decided to employ network > interface bonding to scale over a single GigE. > > The Sun X4150 server has 2xIntel E5450 QuadCore CPUs and a total of four > built-in e1000e interfaces, which I grouped into two bond interfaces. > > With kernel 2.6.23.1, everything works fine, but the system locked up > after a few days. > > With kernel 2.6.28.7/2.6.29.1, I get 10-20% packet loss. I get packet loss > as soon as I put a classful qdisc, even prio, without even having any > classes or filters. TC prio statistics report lots of drops, around 10k per > sec. With exactly the same setup on 2.6.23, the number of drops is only 50 > per sec. > > On both kernels, the system is running with at least 70% idle CPU. > The network interrupts are distributed accross the cores. > > I thought it was a e1000e driver issue, but tweaking e1000e ring buffers > didn't help. I tried using e1000 on 2.6.28 by adding necessary PCI IDs, > I tried running on a different server with bnx cards, I tried disabling > NO_HZ and HRTICK, but still I have the same problem. > > However, if I don't utilize bond, but just apply rules on normal ethX > interfaces, there is no packet loss with 2.6.28/29. > > So, the problem appears only when I use 2.6.28/29 + bond + classful tc > combination. > > Any ideas ?