From owner-freebsd-net@FreeBSD.ORG Tue Dec 16 02:57:11 2003 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B61B316A4CE for ; Tue, 16 Dec 2003 02:57:11 -0800 (PST) Received: from guard.polynet.lviv.ua (guard.polynet.lviv.ua [217.9.2.1]) by mx1.FreeBSD.org (Postfix) with SMTP id ED04043D3F for ; Tue, 16 Dec 2003 02:57:02 -0800 (PST) (envelope-from akorud@polynet.lviv.ua) Received: (qmail 49532 invoked from network); 16 Dec 2003 10:57:00 -0000 Received: from eaux.polynet.lviv.ua (HELO localhost) (217.9.2.4) by 217.9.2.1 with SMTP; 16 Dec 2003 10:57:00 -0000 Received: from ip-81-210-9-34.netia.com.pl (ip-81-210-9-34.netia.com.pl [81.210.9.34]) by isp.polynet.lviv.ua (IMP) with HTTP for <.akorud.netadmin.lp@postoffice.polynet.lviv.ua>; Tue, 16 Dec 2003 12:56:59 +0200 Message-ID: <1071572219.3fdee4fbdadc5@isp.polynet.lviv.ua> Date: Tue, 16 Dec 2003 12:56:59 +0200 From: Andriy Korud To: DrumFire References: <1071564482.3fdec6c2ac5fb@isp.polynet.lviv.ua> <3FDED125.4000304@fsn.hu> <1071567611.3fded2fb8d601@isp.polynet.lviv.ua> <20031216104623.328be6bf.dpphln@tin.it> In-Reply-To: <20031216104623.328be6bf.dpphln@tin.it> MIME-Version: 1.0 Content-Type: text/plain; charset=KOI8-U Content-Transfer-Encoding: 8bit User-Agent: Internet Messaging Program (IMP) 3.2.2 cc: freebsd-net@freebsd.org Subject: Re: Large scale NAT problems X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 16 Dec 2003 10:57:11 -0000 γΙΤΥΐ DrumFire : > On Tue, 16 Dec 2003 11:40:11 +0200 > Andriy Korud wrote: > > First of try OpenBSD pf, that works only on a 5.x-Release, > try to disable device polling in your kernel configuration. > > I've made some test with device_polling enabled, and I have > less performance than with device_polling disabled. > With disabled polling the situating was the same, the only difference is that 'systat -v 1' shows ~3000 of em0 interrupts/s (with polling_enaled - 0 em0 interrupts and 2000 timer interrupts/s). Andriy