From mboxrd@z Thu Jan 1 00:00:00 1970 From: Denys Fedoryshchenko Subject: Re: [PATCH] Re: SFQ depth limit Date: Sun, 29 Jun 2008 22:38:26 +0300 Message-ID: <200806292238.26445.denys@visp.net.lb> References: <20080629191113.GA8817@ami.dom.local> Mime-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org To: Jarek Poplawski Return-path: Received: from relay2.globalproof.net ([194.146.153.25]:59431 "EHLO relay2.globalproof.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1762324AbYF2TiN (ORCPT ); Sun, 29 Jun 2008 15:38:13 -0400 In-Reply-To: <20080629191113.GA8817@ami.dom.local> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: On Sunday 29 June 2008 22:11, Jarek Poplawski wrote: > If it's with vanilla kernel something is wrong, but I couldn't > reproduce this: probably some additianal data is needed. BTW, > I see this "flows" number above isn't very useful, as it always > repeats "limit". I attach a patch proposal to change this. No it is ok, since filter is for protocol IP, ARP will not work. Thats what i found. Incorrect QoS settings can cause network breakage, thats it :-) I will try to test patch ASAP on real load. -- ------ Technical Manager Virtual ISP S.A.L. Lebanon