From mboxrd@z Thu Jan 1 00:00:00 1970 From: Patrick McHardy Subject: Re: netfilter queue throughput slowdown Date: Thu, 30 Jun 2011 13:59:22 +0200 Message-ID: <4E0C651A.1000300@trash.net> References: <1309340843.2532.112.camel@edumazet-laptop> <1309342096.2532.116.camel@edumazet-laptop> <4E0C15A3.9050609@yandex.ru> <1309416426.2532.119.camel@edumazet-laptop> <4E0C278B.7010403@yandex.ru> <1309433652.1994.7.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Kuzin Andrey , Anders Nilsson Plymoth , netfilter-devel To: Eric Dumazet Return-path: Received: from stinky.trash.net ([213.144.137.162]:44473 "EHLO stinky.trash.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751105Ab1F3L70 (ORCPT ); Thu, 30 Jun 2011 07:59:26 -0400 In-Reply-To: <1309433652.1994.7.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> Sender: netfilter-devel-owner@vger.kernel.org List-ID: Am 30.06.2011 13:34, schrieb Eric Dumazet: > Le jeudi 30 juin 2011 =C3=A0 11:36 +0400, Kuzin Andrey a =C3=A9crit : >=20 >> Every day netfilter code become more and more difficult to understa= nd.=20 >> IPQ mechanism don't have >> this problems, migration to NFQUEUE by simply modifications of funct= ion=20 >> names in original program >> code led to these problems. I think it very hard to find this error = in=20 >> netfilter code and may be sometimes >> NFQUEUE will be rewritten from scratch to NGQUEUE (next generation q= ueue) ;) >> I wrote this patch as simply as possible (one-hour solution) to solv= e=20 >> the problem for the our paid services. >> Early no one netfilter developer did not pay any attention to messag= es=20 >> about this problem. >> >=20 > Wow wow wow... >=20 > Maybe these netfilter guys you blame had some paid job to do at the t= ime > you sent your bug report ? Or only you have real paid services ? >=20 > For the record, I also used NFQUEUE and never hit a single problem. >=20 > Maybe I was just lucky, I dont know. >=20 > Instead of trying to hide the bug, please be constructive and find a = way > to pinpoint the bug, so that we can fix it for good. Thanks Eric, I agree. Give us data and we'll fix it if really is a bug. The fact that the timeout patch apparently helps indicates that some packets don't receive verdicts. -- To unsubscribe from this list: send the line "unsubscribe netfilter-dev= el" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html