From owner-freebsd-net@FreeBSD.ORG Fri Aug 31 15:54:10 2012 Return-Path: Delivered-To: freebsd-net@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 295A81065673; Fri, 31 Aug 2012 15:54:10 +0000 (UTC) (envelope-from egrosbein@rdtc.ru) Received: from eg.sd.rdtc.ru (eg.sd.rdtc.ru [IPv6:2a03:3100:c:13::5]) by mx1.freebsd.org (Postfix) with ESMTP id 7C4FF8FC17; Fri, 31 Aug 2012 15:54:09 +0000 (UTC) Received: from eg.sd.rdtc.ru (localhost [127.0.0.1]) by eg.sd.rdtc.ru (8.14.5/8.14.5) with ESMTP id q7VFs5OI098479; Fri, 31 Aug 2012 22:54:05 +0700 (NOVT) (envelope-from egrosbein@rdtc.ru) Message-ID: <5040DE1D.7040700@rdtc.ru> Date: Fri, 31 Aug 2012 22:54:05 +0700 From: Eugene Grosbein User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; ru-RU; rv:1.9.2.13) Gecko/20110112 Thunderbird/3.1.7 MIME-Version: 1.0 To: Adrian Chadd References: <1865271844.20120829131610@serebryakov.spb.ru> <1807373989.20120829223125@serebryakov.spb.ru> <20120830152726.A33776@sola.nimnet.asn.au> <534292400.20120830131158@serebryakov.spb.ru> <20120831180721.GB3208@michelle.cdnetworks.com> <50404957.302@rdtc.ru> <5040508D.9080107@rdtc.ru> In-Reply-To: Content-Type: text/plain; charset=KOI8-R Content-Transfer-Encoding: 8bit Cc: pyunyh@gmail.com, freebsd-net@freebsd.org, Lev Serebryakov , Ian Smith Subject: Re: Bad routing performance on 500Mhz Geode LX with CURRENT, ipfw and mpd5 X-BeenThere: freebsd-net@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Networking and TCP/IP with FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 31 Aug 2012 15:54:10 -0000 31.08.2012 13:54, Adrian Chadd пишет: > Just as a data point - disable preemption and try again? I've rebuilt by kernel with SCHED_ULE and excluded PREEMPTION. Stock driver works without changes in behaviour and driver from HEAD now works very similar to old one: LA is not higher than 2 and userland is pretty responsive. Also, transfer speed with new driver is several percent more. That's good. Care to explain such dramatic difference for new driver with/without PREEMPTION for relatively slow uniprocessor system? > And run 4BSD + no preemption, try again? I'll try that too in short time. Eugene Grosbein