From owner-freebsd-stable@FreeBSD.ORG Wed Feb 27 20:09:25 2008 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 983A81065693 for ; Wed, 27 Feb 2008 20:09:25 +0000 (UTC) (envelope-from hk@alogis.com) Received: from alogis.com (firewall.solit-ag.de [212.184.102.1]) by mx1.freebsd.org (Postfix) with ESMTP id 3C1B78FC15 for ; Wed, 27 Feb 2008 20:09:25 +0000 (UTC) (envelope-from hk@alogis.com) Received: from alogis.com (localhost [127.0.0.1]) by alogis.com (8.13.4/8.13.1) with ESMTP id m1RK9NkR028886; Wed, 27 Feb 2008 21:09:23 +0100 (CET) (envelope-from hk@alogis.com) Received: (from hk@localhost) by alogis.com (8.13.4/8.13.1/Submit) id m1RK9Nas028885; Wed, 27 Feb 2008 21:09:23 +0100 (CET) (envelope-from hk) Date: Wed, 27 Feb 2008 21:09:23 +0100 From: Holger Kipp To: freebsd-stable@freebsd.org Message-ID: <20080227200923.GA28690@intserv.int1.b.intern> References: <20080227104942.GA14530@intserv.int1.b.intern> <200802271452.m1REqJ6H059687@lava.sentex.ca> <20080227195058.GA27997@intserv.int1.b.intern> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080227195058.GA27997@intserv.int1.b.intern> User-Agent: Mutt/1.4.2.1i Cc: Subject: Re: [solved!] Re: em very slow, shared irq... on 6.2p8 X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 27 Feb 2008 20:09:25 -0000 On Wed, Feb 27, 2008 at 08:50:58PM +0100, Holger Kipp wrote: > On Wed, Feb 27, 2008 at 09:50:16AM -0500, Mike Tancsa wrote: > > more details below. as it currently is, polling seems to do > the trick, however handling several em-interfaces with the > same irq (mind you, it is pci) shouldn't cause delays of > up to 1.5 seconds for a simple ping... Therefore I consider > using polling for a nearly idle system more a workaround > than a solution to this problem :-( [...] > with msi enabled (via sysctl) I get > > 33 packets transmitted, 33 packets received, 0% packet loss > round-trip min/avg/max/stddev = 1.865/156.421/1339.841/239.375 ms > > so looks equally bad (I don't consider 30-40 packets a meaningful sample). > I don't know if it makes any differences if switched on directly in > loader.conf, though. have now activated msi in loader.conf and get very good results again. 38 packets transmitted, 38 packets received, 0% packet loss round-trip min/avg/max/stddev = 0.291/0.425/0.595/0.067 ms without polling activated. So it was msi after all I needed here. Maybe this should go into docu for em or ifconfig? > enabling polling (withous MSI) gives > > 30 packets transmitted, 30 packets received, 0% packet loss > round-trip min/avg/max/stddev = 0.366/0.790/1.339/0.290 ms this is still the same with msi activated in loader.conf Best regards, Holger Kipp