From owner-freebsd-performance@FreeBSD.ORG Sun Oct 22 17:03:50 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 28B5316A412; Sun, 22 Oct 2006 17:03:50 +0000 (UTC) (envelope-from vdemart1@tin.it) Received: from vsmtp12.tin.it (vsmtp12.tin.it [212.216.176.206]) by mx1.FreeBSD.org (Postfix) with ESMTP id 236C343D64; Sun, 22 Oct 2006 17:03:42 +0000 (GMT) (envelope-from vdemart1@tin.it) Received: from [10.155.100.8] (87.20.229.20) by vsmtp12.tin.it (7.2.072.1) (authenticated as vdemart1@tin.it) id 452629DE0070DAF2; Sun, 22 Oct 2006 19:03:36 +0200 From: vittorio To: freebsd-performance@freebsd.org, freebsd-database@freebsd.org Date: Sun, 22 Oct 2006 19:03:06 +0000 User-Agent: KMail/1.9.4 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200610221903.06526.vdemart1@tin.it> Cc: Subject: Improving performance of postgresql X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 22 Oct 2006 17:03:50 -0000 Under freebsd 6.1 on a pentium 4 with 256 MB I compiled and installed a postgresql (now 8.0.8) server which has been running wonderfully. I tailored the conf files to tune the server with my hardware according to the many suggestions I read in the net which are OS-independent that is that apply to any *nix (or better linux-centric). Now I would like to know if for a postgresql server there are settings more ** freebsd specif ic ** to improve performance. Ciao Vittorio. From owner-freebsd-performance@FreeBSD.ORG Sun Oct 22 23:15:21 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 50E8116A403 for ; Sun, 22 Oct 2006 23:15:21 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from ciao.gmane.org (main.gmane.org [80.91.229.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0E9DB43D60 for ; Sun, 22 Oct 2006 23:15:09 +0000 (GMT) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from root by ciao.gmane.org with local (Exim 4.43) id 1GbmX0-00038P-Ox for freebsd-performance@freebsd.org; Mon, 23 Oct 2006 01:15:02 +0200 Received: from 89-172-52-23.adsl.net.t-com.hr ([89.172.52.23]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Mon, 23 Oct 2006 01:15:02 +0200 Received: from ivoras by 89-172-52-23.adsl.net.t-com.hr with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Mon, 23 Oct 2006 01:15:02 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-performance@freebsd.org From: Ivan Voras Date: Mon, 23 Oct 2006 01:13:02 +0200 Lines: 8 Message-ID: References: <200610221903.06526.vdemart1@tin.it> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@sea.gmane.org X-Gmane-NNTP-Posting-Host: 89-172-52-23.adsl.net.t-com.hr User-Agent: Thunderbird 1.5.0.7 (Windows/20060909) In-Reply-To: <200610221903.06526.vdemart1@tin.it> Sender: news Cc: freebsd-database@freebsd.org Subject: Re: Improving performance of postgresql X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 22 Oct 2006 23:15:21 -0000 vittorio wrote: > Now I would like to know if for a postgresql server there are settings more ** > freebsd specif ic ** to improve performance. You can start from here: http://wiki.freebsd.org/Performance, in particular read the MySQL page but ignore all points regarding threading and threads. From owner-freebsd-performance@FreeBSD.ORG Mon Oct 23 06:21:08 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7566316A403 for ; Mon, 23 Oct 2006 06:21:08 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from wx-out-0506.google.com (wx-out-0506.google.com [66.249.82.234]) by mx1.FreeBSD.org (Postfix) with ESMTP id 03D6843D4C for ; Mon, 23 Oct 2006 06:21:07 +0000 (GMT) (envelope-from adrian.chadd@gmail.com) Received: by wx-out-0506.google.com with SMTP id t4so1515459wxc for ; Sun, 22 Oct 2006 23:21:07 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:sender:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition:x-google-sender-auth; b=GIgQSRgxbhsPK/1CWh/AqBHddGQF9OMq+D/3ZI9embSVapjVsIyldqn0ThKkow2umwSK6CW5Vxy8YpoA/rLx/L1LcG40WeNZaB6+aM9n9pgX5LlEUw9qTjitmSbWqLJkjzArtHhmV+yxeWa9JHmCs60doa/Ra5MuKjv7uY4lAK8= Received: by 10.90.80.8 with SMTP id d8mr1870942agb; Sun, 22 Oct 2006 23:21:07 -0700 (PDT) Received: by 10.90.66.16 with HTTP; Sun, 22 Oct 2006 23:21:07 -0700 (PDT) Message-ID: Date: Mon, 23 Oct 2006 14:21:07 +0800 From: "Adrian Chadd" Sender: adrian.chadd@gmail.com To: freebsd-performance@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline X-Google-Sender-Auth: 63cc204d4e5db403 Subject: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Oct 2006 06:21:08 -0000 Hi all, I'm currently fiddling with writing a 'simple' TCP proxy for FreeBSD which uses kqueue to handle IO. I've been looking for examples of kqueue code which uses all the cute features of kqueue to "optimise" things, eg "hinting" at send/recv size, whether EOF has been seen, setting the buffer low watermark for triggering, that kind of thing. All I've found thus far (and I hope I'm not to blame for my initial hackings of kqueue in a few bits of software!) are simple level-triggered uses which don't seem much better than Linux epoll or Solaris /dev/poll. Even libevent uses it pretty naively. Has anyone come across some network software which uses kqueue "differently" to the above ? Thanks, Adrian -- Adrian Chadd - adrian@freebsd.org From owner-freebsd-performance@FreeBSD.ORG Mon Oct 23 17:45:24 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C0C7016A40F; Mon, 23 Oct 2006 17:45:24 +0000 (UTC) (envelope-from drechsau@Geeks.ORG) Received: from mail.geeks.org (jacobs.geeks.org [204.153.247.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id 216FF43DAE; Mon, 23 Oct 2006 17:44:54 +0000 (GMT) (envelope-from drechsau@Geeks.ORG) Received: by mail.geeks.org (Postfix, from userid 1000) id 31A76159059; Mon, 23 Oct 2006 12:44:54 -0500 (CDT) Date: Mon, 23 Oct 2006 12:44:54 -0500 From: Mike Horwath To: Adrian Chadd Message-ID: <20061023174454.GB48434@Geeks.ORG> Mail-Followup-To: Adrian Chadd , freebsd-performance@freebsd.org References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-PGP-Fingerprint: D8 24 CC E6 47 5F E4 60 BF B7 6E FA BF C7 6E C5 X-GPG-Fingerprint: 6A89 E78A B8B1 69D9 8CDB E966 4A5A C3F9 A1B0 C381 User-Agent: mutt-ng/devel-r804 (FreeBSD) Cc: freebsd-performance@freebsd.org Subject: Re: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Oct 2006 17:45:24 -0000 On Mon, Oct 23, 2006 at 02:21:07PM +0800, Adrian Chadd wrote: > All I've found thus far (and I hope I'm not to blame for my initial > hackings of kqueue in a few bits of software!) are simple > level-triggered uses which don't seem much better than Linux epoll or > Solaris /dev/poll. Even libevent uses it pretty naively. > > Has anyone come across some network software which uses kqueue > "differently" to the above ? I haven't dug into it yet, but dovecot is using kqueue() on FreeBSD. http://dovecot.org/ -- Mike Horwath, reachable via drechsau@Geeks.ORG From owner-freebsd-performance@FreeBSD.ORG Mon Oct 23 23:49:51 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E812D16A4D0 for ; Mon, 23 Oct 2006 23:49:51 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from wx-out-0506.google.com (wx-out-0506.google.com [66.249.82.234]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6944943D9C for ; Mon, 23 Oct 2006 23:49:48 +0000 (GMT) (envelope-from adrian.chadd@gmail.com) Received: by wx-out-0506.google.com with SMTP id i27so1918520wxd for ; Mon, 23 Oct 2006 16:49:47 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:sender:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; b=NvRxoAfMDIsf/cgU6KVsBXHuk1igC4Ec++m7gPftMLazGvWf//mCEcpzc5NkBlZf4jMZx7sUudL0DpE8N9vThu1j8GuumgkcCZM+ffW0nWMufpS7H9EY63sfdq71kWZ9yPZ1Pc2EMJnIB12qQYfVT0W6NslJDWWLBe5QV+8crdU= Received: by 10.90.63.16 with SMTP id l16mr2796503aga; Mon, 23 Oct 2006 16:49:47 -0700 (PDT) Received: by 10.90.66.16 with HTTP; Mon, 23 Oct 2006 16:49:47 -0700 (PDT) Message-ID: Date: Tue, 24 Oct 2006 07:49:47 +0800 From: "Adrian Chadd" Sender: adrian.chadd@gmail.com To: "Adrian Chadd" , freebsd-performance@freebsd.org In-Reply-To: <20061023174454.GB48434@Geeks.ORG> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20061023174454.GB48434@Geeks.ORG> X-Google-Sender-Auth: d8bf66404655305b Cc: Subject: Re: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 23 Oct 2006 23:49:52 -0000 On 10/24/06, Mike Horwath wrote: > > I haven't dug into it yet, but dovecot is using kqueue() on FreeBSD. > > http://dovecot.org/ Its a pretty simplistic use of kevent(); at least it is in 1.0r7 which I have here. (Single submission of events to kevent() rather than bunching them up all into larger updates.) Adrian -- Adrian Chadd - adrian@freebsd.org From owner-freebsd-performance@FreeBSD.ORG Tue Oct 24 00:03:34 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B788516A403; Tue, 24 Oct 2006 00:03:34 +0000 (UTC) (envelope-from drechsau@Geeks.ORG) Received: from mail.geeks.org (jacobs.geeks.org [204.153.247.1]) by mx1.FreeBSD.org (Postfix) with ESMTP id ED95543D79; Tue, 24 Oct 2006 00:03:28 +0000 (GMT) (envelope-from drechsau@Geeks.ORG) Received: by mail.geeks.org (Postfix, from userid 1000) id 398B215905C; Mon, 23 Oct 2006 19:03:28 -0500 (CDT) Date: Mon, 23 Oct 2006 19:03:28 -0500 From: Mike Horwath To: Adrian Chadd Message-ID: <20061024000328.GA55313@Geeks.ORG> Mail-Followup-To: Adrian Chadd , freebsd-performance@freebsd.org References: <20061023174454.GB48434@Geeks.ORG> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-PGP-Fingerprint: D8 24 CC E6 47 5F E4 60 BF B7 6E FA BF C7 6E C5 X-GPG-Fingerprint: 6A89 E78A B8B1 69D9 8CDB E966 4A5A C3F9 A1B0 C381 User-Agent: mutt-ng/devel-r804 (FreeBSD) Cc: freebsd-performance@freebsd.org Subject: Re: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Oct 2006 00:03:34 -0000 On Tue, Oct 24, 2006 at 07:49:47AM +0800, Adrian Chadd wrote: > On 10/24/06, Mike Horwath wrote: > > > > >I haven't dug into it yet, but dovecot is using kqueue() on FreeBSD. > > > >http://dovecot.org/ > > Its a pretty simplistic use of kevent(); at least it is in 1.0r7 which > I have here. (Single submission of events to kevent() rather than > bunching them up all into larger updates.) Bummer. Sorry it didn't help. -- Mike Horwath, reachable via drechsau@Geeks.ORG From owner-freebsd-performance@FreeBSD.ORG Tue Oct 24 02:30:51 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 525A816A415; Tue, 24 Oct 2006 02:30:51 +0000 (UTC) (envelope-from mark@gaiahost.coop) Received: from biodiesel.gaiahost.coop (biodiesel.gaiahost.coop [64.95.78.120]) by mx1.FreeBSD.org (Postfix) with ESMTP id EF1AF43D4C; Tue, 24 Oct 2006 02:30:50 +0000 (GMT) (envelope-from mark@gaiahost.coop) Received: from gaiahost.coop (host-64-65-195-19.spr.choiceone.net [::ffff:64.65.195.19]) (AUTH: LOGIN mark@hubcapconsulting.com) by biodiesel.gaiahost.coop with esmtp; Mon, 23 Oct 2006 22:30:46 -0400 id 0010C06E.453D7AD6.0000135A Received: by gaiahost.coop (sSMTP sendmail emulation); Mon, 23 Oct 2006 22:30:30 -0400 Date: Mon, 23 Oct 2006 22:30:30 -0400 From: Mark Bucciarelli To: Adrian Chadd Message-ID: <20061024023030.GJ2760@rabbit> Mail-Followup-To: Adrian Chadd , freebsd-performance@freebsd.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline User-Agent: Mutt/1.4.2.1i Cc: freebsd-performance@freebsd.org Subject: Re: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Oct 2006 02:30:51 -0000 On Mon, Oct 23, 2006 at 02:21:07PM +0800, Adrian Chadd wrote: > > Has anyone come across some network software which uses kqueue > "differently" to the above ? lighttpd uses kqueue. Don't know how "different" it is. m From owner-freebsd-performance@FreeBSD.ORG Tue Oct 24 03:03:35 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AB66516A403 for ; Tue, 24 Oct 2006 03:03:35 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from wx-out-0506.google.com (wx-out-0506.google.com [66.249.82.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9E0B443D4C for ; Tue, 24 Oct 2006 03:03:34 +0000 (GMT) (envelope-from adrian.chadd@gmail.com) Received: by wx-out-0506.google.com with SMTP id i27so1970293wxd for ; Mon, 23 Oct 2006 20:03:34 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:sender:to:subject:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references:x-google-sender-auth; b=eA6vFRSzkLFIv+Q4nNBP5VWv2DCHRgeSC8CJQQbA2AJs1tdMF7NHPd4mC7Bf50EUIzDH1pEPigIfNYLTV5cPy1LugIcIiRFztxI4QFfszYdvNfwu8BGMrcr+/AnmaWIxcPyCtzgfriNyHyyOnmQcN+QlpMBcPNE/YnrGEF45L8E= Received: by 10.90.90.16 with SMTP id n16mr2760829agb; Mon, 23 Oct 2006 20:03:34 -0700 (PDT) Received: by 10.90.66.16 with HTTP; Mon, 23 Oct 2006 20:03:34 -0700 (PDT) Message-ID: Date: Tue, 24 Oct 2006 11:03:34 +0800 From: "Adrian Chadd" Sender: adrian.chadd@gmail.com To: "Adrian Chadd" , freebsd-performance@freebsd.org In-Reply-To: <20061024023030.GJ2760@rabbit> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <20061024023030.GJ2760@rabbit> X-Google-Sender-Auth: cf696731bbdbdcf5 Cc: Subject: Re: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Oct 2006 03:03:35 -0000 On 10/24/06, Mark Bucciarelli wrote: > On Mon, Oct 23, 2006 at 02:21:07PM +0800, Adrian Chadd wrote: > > > > Has anyone come across some network software which uses kqueue > > "differently" to the above ? > > lighttpd uses kqueue. Don't know how "different" it is. Again its pretty simplistic - individual events are registered by using kevent() calls; kevent() is then called to process all the results. I wonder how much of a boost there'd be between this model as the 'nicer' kevent model. Hm, I'll have to give it a shot and compare numbers. Thanks. Adrian -- Adrian Chadd - adrian@freebsd.org From owner-freebsd-performance@FreeBSD.ORG Tue Oct 24 15:23:17 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 90E2616A407 for ; Tue, 24 Oct 2006 15:23:17 +0000 (UTC) (envelope-from mike@sentex.net) Received: from smarthost2.sentex.ca (smarthost2.sentex.ca [205.211.164.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1072543D49 for ; Tue, 24 Oct 2006 15:22:51 +0000 (GMT) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by smarthost2.sentex.ca (8.13.8/8.13.8) with ESMTP id k9OEMPGJ046752 for ; Tue, 24 Oct 2006 10:22:25 -0400 (EDT) (envelope-from mike@sentex.net) Received: from mdt-xp.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.13.6/8.13.3) with ESMTP id k9OEMPwv014555 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Tue, 24 Oct 2006 10:22:25 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <7.0.1.0.0.20061024100908.0688fd68@sentex.net> X-Mailer: QUALCOMM Windows Eudora Version 7.0.1.0 Date: Tue, 24 Oct 2006 10:22:14 -0400 To: freebsd-performance@freebsd.org From: Mike Tancsa In-Reply-To: <7.0.1.0.0.20061020161447.16083e08@sentex.net> References: <7.0.1.0.0.20061020104944.144d9068@sentex.net> <20061020200638.GA18727@sandvine.com> <7.0.1.0.0.20061020161447.16083e08@sentex.net> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Subject: Spam-Assassin Benchmarks (was Re: LINUX vs FreeBSD mysql performance using a large RT database X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Oct 2006 15:23:17 -0000 At 04:21 PM 10/20/2006, Mike Tancsa wrote: >The next set of comparisons I want to run is in our spam >scanners. The boxes which operate in round robin make heavy use of mysql, DNS OK, we are just getting ready to run some tests for this setup. SpamAssassin has some built in benchmarking that we will use. e.g. scan a set 500 spam messages, scan 5 sets using 5 different processes at the same time, scan 10 etc and measure time taken. The applications make heavy use of perl and mysql as well as netio (numerous DNS lookups) For FreeBSD tweaking, does anyone have any suggestions or requests what we should tweak or test to see how things perform ? Anecdotal evidence shows us that AMD64, consistently runs at a higher load avg than the others, despite having an equal mix of spam thrown at it. One thing I am not sure of however is if this is truly slower (I suspect yes) or if there are differences in how load average is calculated on i386 vs AMD64 ? ---Mike From owner-freebsd-performance@FreeBSD.ORG Tue Oct 24 15:44:53 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4076516A415; Tue, 24 Oct 2006 15:44:53 +0000 (UTC) (envelope-from mark@gaiahost.coop) Received: from biodiesel.gaiahost.coop (biodiesel.gaiahost.coop [64.95.78.120]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1DDFD43D6A; Tue, 24 Oct 2006 15:44:48 +0000 (GMT) (envelope-from mark@gaiahost.coop) Received: from gaiahost.coop (host-64-65-195-19.spr.choiceone.net [::ffff:64.65.195.19]) (AUTH: LOGIN mark@hubcapconsulting.com) by biodiesel.gaiahost.coop with esmtp; Tue, 24 Oct 2006 11:44:47 -0400 id 008D004C.453E34EF.000016A4 Received: by gaiahost.coop (sSMTP sendmail emulation); Tue, 24 Oct 2006 11:44:49 -0400 Date: Tue, 24 Oct 2006 11:44:49 -0400 From: Mark Bucciarelli To: Adrian Chadd Message-ID: <20061024154449.GU2760@rabbit> Mail-Followup-To: Adrian Chadd , freebsd-performance@freebsd.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline User-Agent: Mutt/1.4.2.1i Cc: freebsd-performance@freebsd.org Subject: Re: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Oct 2006 15:44:53 -0000 On Tue, Oct 24, 2006 at 11:03:34AM +0800, Adrian Chadd wrote: > On 10/24/06, Mark Bucciarelli wrote: > >On Mon, Oct 23, 2006 at 02:21:07PM +0800, Adrian Chadd wrote: > >> > >> Has anyone come across some network software which uses kqueue > >> "differently" to the above ? > > > >lighttpd uses kqueue. Don't know how "different" it is. > > Again its pretty simplistic - individual events are registered by > using kevent() calls; kevent() is then called to process all the > results. > > I wonder how much of a boost there'd be between this model as the > 'nicer' kevent model. Hm, I'll have to give it a shot and compare > numbers. Thanks. If you do this comparison for lighttpd, I would be interested in the results. m From owner-freebsd-performance@FreeBSD.ORG Tue Oct 24 18:40:17 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DC1F216A4CA for ; Tue, 24 Oct 2006 18:40:17 +0000 (UTC) (envelope-from ianchov@gmail.com) Received: from nf-out-0910.google.com (nf-out-0910.google.com [64.233.182.191]) by mx1.FreeBSD.org (Postfix) with ESMTP id 60BF443DF2 for ; Tue, 24 Oct 2006 18:39:32 +0000 (GMT) (envelope-from ianchov@gmail.com) Received: by nf-out-0910.google.com with SMTP id p77so303536nfc for ; Tue, 24 Oct 2006 11:39:29 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:in-reply-to:mime-version:content-type:references; b=HqjfEUjCds1tx/O3d365y/L+NoiI624n39Guvo7yPFTVbDLb22UknBv8YEOpJgMzGNTPw1ulW7MXZJK5sVlbxU9UghBVF9AQ5yhkQBW0ELt+KJf2ImYjBxNUdD7NWHLmTJehpq1dZGSE7QCZ2mAqqkk26zRcA/+0G6vesJLLgZE= Received: by 10.49.75.2 with SMTP id c2mr1756696nfl; Tue, 24 Oct 2006 11:39:29 -0700 (PDT) Received: by 10.49.36.13 with HTTP; Tue, 24 Oct 2006 11:39:29 -0700 (PDT) Message-ID: <18e02bd30610241139j905914ew1b0d067ad58b2b43@mail.gmail.com> Date: Tue, 24 Oct 2006 21:39:29 +0300 From: "Iantcho Vassilev" To: "Adrian Chadd" , freebsd-performance@freebsd.org In-Reply-To: <20061024154449.GU2760@rabbit> MIME-Version: 1.0 References: <20061024154449.GU2760@rabbit> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Subject: Re: kqueue examples? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 24 Oct 2006 18:40:18 -0000 On 10/24/06, Mark Bucciarelli wrote: > > On Tue, Oct 24, 2006 at 11:03:34AM +0800, Adrian Chadd wrote: > > On 10/24/06, Mark Bucciarelli wrote: > > >On Mon, Oct 23, 2006 at 02:21:07PM +0800, Adrian Chadd wrote: > > >> > > >> Has anyone come across some network software which uses kqueue > > >> "differently" to the above ? > > > > > >lighttpd uses kqueue. Don't know how "different" it is. > > > > Again its pretty simplistic - individual events are registered by > > using kevent() calls; kevent() is then called to process all the > > results. > > > > I wonder how much of a boost there'd be between this model as the > > 'nicer' kevent model. Hm, I'll have to give it a shot and compare > > numbers. Thanks. > > If you do this comparison for lighttpd, I would be interested in > the results. > > Absolutely... I`ll be very interested too.. From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 03:00:09 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 51C3C16A416 for ; Wed, 25 Oct 2006 03:00:09 +0000 (UTC) (envelope-from kreios@gmail.com) Received: from py-out-1112.google.com (py-out-1112.google.com [64.233.166.182]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9130343D8C for ; Wed, 25 Oct 2006 03:00:01 +0000 (GMT) (envelope-from kreios@gmail.com) Received: by py-out-1112.google.com with SMTP id c59so13764pyc for ; Tue, 24 Oct 2006 19:59:57 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=l1iQY6aI8A6BinyKMCwS34rGdNznCeZcJsiZ1JVUFsKXum1kJ6sVxBAjcDzuIOX+JOQWBHIE80JZYiwTfT57rJEbfUbgGhbdS/ruiO4f0ajEr2v8cmXni8c89R//rltE3zGJ6feLGiCC9gd9bNaH7MNYPsZxHn5k9DooCK2uITM= Received: by 10.35.82.16 with SMTP id j16mr67575pyl; Tue, 24 Oct 2006 19:59:57 -0700 (PDT) Received: by 10.35.33.20 with HTTP; Tue, 24 Oct 2006 19:59:57 -0700 (PDT) Message-ID: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> Date: Tue, 24 Oct 2006 21:59:57 -0500 From: kreios@gmail.com To: performance@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Cc: Subject: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 03:00:09 -0000 I am running some performance tests on named to see how it performs with different configurations on FreeBSD and figured I would share the first results. The first tests are for serving up static data. System: Supermicro PDSMi Motherboard 1G Memory Intel Pentium D CPU 3.40GHz Intel Gigibit NIC Bind 9.2.3 OS UP UP+P MP MP+P MP+TP MP+TT MP+TP+P MP+TT+P ------------------------------------------------------------------------------- FreeBSD 4.11 28455 28370 28976 X X X X X FreeBSD 6.1 29074 34260 34635 35730 17846 38780 19776 44188 FreeBSD Stable 30190 34707 33294 36651 18893 39374 19449 44169 FreeBSD Current 30707 34029 32300 33689 15535 40554 13886 42071 Ubuntu 6.06 X X X X X 37294 X X UP = Uni-processor Kernel MP = Multi-processor Kernel P = Device Polling TP = Threaded Bind using libpthread TT = Threaded Bind using libthr -- Dave From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 04:29:20 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from localhost.my.domain (localhost [127.0.0.1]) by hub.freebsd.org (Postfix) with ESMTP id E628F16A407; Wed, 25 Oct 2006 04:29:19 +0000 (UTC) (envelope-from davidxu@freebsd.org) From: David Xu To: freebsd-performance@freebsd.org Date: Wed, 25 Oct 2006 12:29:16 +0800 User-Agent: KMail/1.8.2 References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> In-Reply-To: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200610251229.16919.davidxu@freebsd.org> Cc: performance@freebsd.org, kreios@gmail.com Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 04:29:20 -0000 On Wednesday 25 October 2006 10:59, kreios@gmail.com wrote: > I am running some performance tests on named to see how it performs > with different configurations on FreeBSD and figured I would share the > first results. The first tests are for serving up static data. > > System: > Supermicro PDSMi Motherboard > 1G Memory > Intel Pentium D CPU 3.40GHz > Intel Gigibit NIC > Bind 9.2.3 > > OS UP UP+P MP MP+P MP+TP MP+TT MP+TP+P > MP+TT+P > --------------------------------------------------------------------------- >---- FreeBSD 4.11 28455 28370 28976 X X X X > X FreeBSD 6.1 29074 34260 34635 35730 17846 38780 19776 > 44188 FreeBSD Stable 30190 34707 33294 36651 18893 39374 19449 > 44169 FreeBSD Current 30707 34029 32300 33689 15535 40554 > 13886 42071 Ubuntu 6.06 X X X X X 37294 > X X > > UP = Uni-processor Kernel > MP = Multi-processor Kernel > P = Device Polling > TP = Threaded Bind using libpthread > TT = Threaded Bind using libthr > > -- > Dave Thanks for your benchmark result! so it blows away the rumor that our thread library is slow. David Xu From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 04:29:20 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from localhost.my.domain (localhost [127.0.0.1]) by hub.freebsd.org (Postfix) with ESMTP id E628F16A407; Wed, 25 Oct 2006 04:29:19 +0000 (UTC) (envelope-from davidxu@freebsd.org) From: David Xu To: freebsd-performance@freebsd.org Date: Wed, 25 Oct 2006 12:29:16 +0800 User-Agent: KMail/1.8.2 References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> In-Reply-To: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200610251229.16919.davidxu@freebsd.org> Cc: performance@freebsd.org, kreios@gmail.com Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 04:29:20 -0000 On Wednesday 25 October 2006 10:59, kreios@gmail.com wrote: > I am running some performance tests on named to see how it performs > with different configurations on FreeBSD and figured I would share the > first results. The first tests are for serving up static data. > > System: > Supermicro PDSMi Motherboard > 1G Memory > Intel Pentium D CPU 3.40GHz > Intel Gigibit NIC > Bind 9.2.3 > > OS UP UP+P MP MP+P MP+TP MP+TT MP+TP+P > MP+TT+P > --------------------------------------------------------------------------- >---- FreeBSD 4.11 28455 28370 28976 X X X X > X FreeBSD 6.1 29074 34260 34635 35730 17846 38780 19776 > 44188 FreeBSD Stable 30190 34707 33294 36651 18893 39374 19449 > 44169 FreeBSD Current 30707 34029 32300 33689 15535 40554 > 13886 42071 Ubuntu 6.06 X X X X X 37294 > X X > > UP = Uni-processor Kernel > MP = Multi-processor Kernel > P = Device Polling > TP = Threaded Bind using libpthread > TT = Threaded Bind using libthr > > -- > Dave Thanks for your benchmark result! so it blows away the rumor that our thread library is slow. David Xu From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 07:35:14 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A39BD16A407 for ; Wed, 25 Oct 2006 07:35:14 +0000 (UTC) (envelope-from xdivac02@stud.fit.vutbr.cz) Received: from eva.fit.vutbr.cz (eva.fit.vutbr.cz [147.229.176.14]) by mx1.FreeBSD.org (Postfix) with ESMTP id F013043D5C for ; Wed, 25 Oct 2006 07:35:13 +0000 (GMT) (envelope-from xdivac02@stud.fit.vutbr.cz) Received: from eva.fit.vutbr.cz (localhost [127.0.0.1]) by eva.fit.vutbr.cz (envelope-from xdivac02@eva.fit.vutbr.cz) (8.13.8/8.13.7) with ESMTP id k9P7ZCGb090413 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Wed, 25 Oct 2006 09:35:12 +0200 (CEST) Received: (from xdivac02@localhost) by eva.fit.vutbr.cz (8.13.8/8.13.3/Submit) id k9P7ZBfY090412; Wed, 25 Oct 2006 09:35:11 +0200 (CEST) Date: Wed, 25 Oct 2006 09:35:11 +0200 From: Divacky Roman To: kreios@gmail.com Message-ID: <20061025073511.GA90244@stud.fit.vutbr.cz> References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> User-Agent: Mutt/1.4.2.2i X-Scanned-By: MIMEDefang 2.57 on 147.229.176.14 Cc: performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 07:35:14 -0000 On Tue, Oct 24, 2006 at 09:59:57PM -0500, kreios@gmail.com wrote: > I am running some performance tests on named to see how it performs > with different configurations on FreeBSD and figured I would share the > first results. The first tests are for serving up static data. > > System: > Supermicro PDSMi Motherboard > 1G Memory > Intel Pentium D CPU 3.40GHz > Intel Gigibit NIC > Bind 9.2.3 > > OS UP UP+P MP MP+P MP+TP MP+TT MP+TP+P > MP+TT+P > ------------------------------------------------------------------------------- > FreeBSD 4.11 28455 28370 28976 X X X X X > FreeBSD 6.1 29074 34260 34635 35730 17846 38780 19776 > 44188 > FreeBSD Stable 30190 34707 33294 36651 18893 39374 19449 > 44169 > FreeBSD Current 30707 34029 32300 33689 15535 40554 13886 > 42071 > Ubuntu 6.06 X X X X X 37294 X X I see regression between -current and -stable. are you sure you tested without any debuging stuff? some performance speedups went in in 7-current also - do you use the same config everywhere? -current GENERIC doesnt have COMPAT_43 for example which miht affect performance (additional locking) etc. roman From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 08:29:47 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B11F116A40F for ; Wed, 25 Oct 2006 08:29:47 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from redbull.bpaserver.net (redbullneu.bpaserver.net [213.198.78.217]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1F44E43D46 for ; Wed, 25 Oct 2006 08:29:46 +0000 (GMT) (envelope-from alexander@leidinger.net) Received: from outgoing.leidinger.net (p54A5FE6C.dip.t-dialin.net [84.165.254.108]) by redbull.bpaserver.net (Postfix) with ESMTP id 950F32E1D8; Wed, 25 Oct 2006 10:29:33 +0200 (CEST) Received: from webmail.leidinger.net (webmail.Leidinger.net [192.168.1.102]) by outgoing.leidinger.net (Postfix) with ESMTP id 6F69B5B622E; Wed, 25 Oct 2006 10:29:30 +0200 (CEST) Received: (from www@localhost) by webmail.leidinger.net (8.13.8/8.13.8/Submit) id k9P8TU8i040888; Wed, 25 Oct 2006 10:29:30 +0200 (CEST) (envelope-from Alexander@Leidinger.net) Received: from pslux.cec.eu.int (pslux.cec.eu.int [158.169.9.14]) by webmail.leidinger.net (Horde MIME library) with HTTP; Wed, 25 Oct 2006 10:29:30 +0200 Message-ID: <20061025102930.lzb3k8x1ooowkog0@webmail.leidinger.net> X-Priority: 3 (Normal) Date: Wed, 25 Oct 2006 10:29:30 +0200 From: Alexander Leidinger To: kreios@gmail.com References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> In-Reply-To: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8; DelSp="Yes"; format="flowed" Content-Disposition: inline Content-Transfer-Encoding: 7bit User-Agent: Internet Messaging Program (IMP) H3 (4.1.3) / FreeBSD-7.0 X-BPAnet-MailScanner-Information: Please contact the ISP for more information X-BPAnet-MailScanner: Found to be clean X-BPAnet-MailScanner-SpamCheck: not spam, SpamAssassin (not cached, score=-2.463, required 6, autolearn=not spam, BAYES_00 -2.60, DK_POLICY_SIGNSOME 0.00, FORGED_RCVD_HELO 0.14) X-BPAnet-MailScanner-From: alexander@leidinger.net X-Spam-Status: No Cc: performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 08:29:47 -0000 Quoting kreios@gmail.com (from Tue, 24 Oct 2006 21:59:57 -0500): > I am running some performance tests on named to see how it performs > with different configurations on FreeBSD and figured I would share the > first results. The first tests are for serving up static data. I added this to http://wiki.freebsd.org/BenchmarkMatrix Bye, Alexander. -- Every day people are straying away from the church and going back to God. -- Lenny Bruce http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID = B0063FE7 http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID = 72077137 From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 08:44:47 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id EB21D16A412 for ; Wed, 25 Oct 2006 08:44:47 +0000 (UTC) (envelope-from BORJAMAR@SARENET.ES) Received: from smtp1.sarenet.es (smtp1.sarenet.es [194.30.0.4]) by mx1.FreeBSD.org (Postfix) with ESMTP id 888CC43D5A for ; Wed, 25 Oct 2006 08:44:47 +0000 (GMT) (envelope-from BORJAMAR@SARENET.ES) Received: from [127.0.0.1] (matahari.sarenet.es [192.148.167.18]) by smtp1.sarenet.es (Postfix) with ESMTP id 5B032110CF; Wed, 25 Oct 2006 10:44:45 +0200 (CEST) In-Reply-To: <20061025102930.lzb3k8x1ooowkog0@webmail.leidinger.net> References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> <20061025102930.lzb3k8x1ooowkog0@webmail.leidinger.net> Mime-Version: 1.0 (Apple Message framework v752.2) X-Priority: 3 (Normal) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Borja Marcos Date: Wed, 25 Oct 2006 10:44:42 +0200 To: Alexander Leidinger X-Mailer: Apple Mail (2.752.2) Cc: performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 08:44:48 -0000 >> I am running some performance tests on named to see how it performs >> with different configurations on FreeBSD and figured I would share >> the >> first results. The first tests are for serving up static data. > > I added this to > http://wiki.freebsd.org/BenchmarkMatrix According to the bind9 port makefile, using threads is _not_ recommended. Specifically, it seems it's a recommendation from ISC # ISC staff has informed me that for 9.3.x, threads are always a bad idea. # Leave the affirmative option for those that want to experiment. It would be a good idea to add this note. It's good to experiment with performance, but people running production servers should be aware of this restriction. Borja. From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 08:59:23 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6102C16A412 for ; Wed, 25 Oct 2006 08:59:23 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from redbull.bpaserver.net (redbullneu.bpaserver.net [213.198.78.217]) by mx1.FreeBSD.org (Postfix) with ESMTP id 69D9643D6D for ; Wed, 25 Oct 2006 08:59:21 +0000 (GMT) (envelope-from alexander@leidinger.net) Received: from outgoing.leidinger.net (p54A5FE6C.dip.t-dialin.net [84.165.254.108]) by redbull.bpaserver.net (Postfix) with ESMTP id BE8E52E255; Wed, 25 Oct 2006 10:57:40 +0200 (CEST) Received: from webmail.leidinger.net (webmail.Leidinger.net [192.168.1.102]) by outgoing.leidinger.net (Postfix) with ESMTP id 366C05B622E; Wed, 25 Oct 2006 10:57:39 +0200 (CEST) Received: (from www@localhost) by webmail.leidinger.net (8.13.8/8.13.8/Submit) id k9P8vd04045651; Wed, 25 Oct 2006 10:57:39 +0200 (CEST) (envelope-from Alexander@Leidinger.net) Received: from pslux.cec.eu.int (pslux.cec.eu.int [158.169.9.14]) by webmail.leidinger.net (Horde MIME library) with HTTP; Wed, 25 Oct 2006 10:57:38 +0200 Message-ID: <20061025105738.hz8rii4p8go84cc4@webmail.leidinger.net> X-Priority: 3 (Normal) Date: Wed, 25 Oct 2006 10:57:38 +0200 From: Alexander Leidinger To: Borja Marcos References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> <20061025102930.lzb3k8x1ooowkog0@webmail.leidinger.net> In-Reply-To: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8; DelSp="Yes"; format="flowed" Content-Disposition: inline Content-Transfer-Encoding: 7bit User-Agent: Internet Messaging Program (IMP) H3 (4.1.3) / FreeBSD-7.0 X-BPAnet-MailScanner-Information: Please contact the ISP for more information X-BPAnet-MailScanner: Found to be clean X-BPAnet-MailScanner-SpamCheck: not spam, SpamAssassin (not cached, timed out) X-BPAnet-MailScanner-From: alexander@leidinger.net X-Spam-Status: No Cc: performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 08:59:23 -0000 Quoting Borja Marcos (from Wed, 25 Oct 2006 10:44:42 +0200): > According to the bind9 port makefile, using threads is _not_ > recommended. Specifically, it seems it's a recommendation from ISC > It would be a good idea to add this note. It's good to experiment with > performance, but people running production servers should be aware of > this restriction. Because I linked to the list positng in the archives, you just added this note to the thread... Bye, Alexander. -- Freedom's just another word for nothing left to lose. -- Kris Kristofferson, "Me and Bobby McGee" http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID = B0063FE7 http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID = 72077137 From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 09:51:09 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4103916A492 for ; Wed, 25 Oct 2006 09:51:09 +0000 (UTC) (envelope-from gnn@neville-neil.com) Received: from mrout3.yahoo.com (mrout3.yahoo.com [216.145.54.173]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2281343D86 for ; Wed, 25 Oct 2006 09:50:57 +0000 (GMT) (envelope-from gnn@neville-neil.com) Received: from minion.local.neville-neil.com (proxy8.corp.yahoo.com [216.145.48.13]) by mrout3.yahoo.com (8.13.6/8.13.6/y.out) with ESMTP id k9P9oaNA087830; Wed, 25 Oct 2006 02:50:36 -0700 (PDT) Date: Wed, 25 Oct 2006 10:50:33 +0100 Message-ID: From: gnn@freebsd.org To: kreios@gmail.com In-Reply-To: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> User-Agent: Wanderlust/2.14.0 (Africa) SEMI/1.14.6 (Maruoka) FLIM/1.14.8 (=?ISO-8859-4?Q?Shij=F2?=) APEL/10.6 Emacs/22.0.50 (i386-apple-darwin8.7.1) MULE/5.0 (SAKAKI) MIME-Version: 1.0 (generated by SEMI 1.14.6 - "Maruoka") Content-Type: text/plain; charset=US-ASCII Cc: performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 09:51:09 -0000 At Tue, 24 Oct 2006 21:59:57 -0500, kreios@gmail.com wrote: > > I am running some performance tests on named to see how it performs > with different configurations on FreeBSD and figured I would share the > first results. The first tests are for serving up static data. Thanks very much for this! Can we possible see a dmesg output as well, just for completeness? Thanks, George From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 13:56:33 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2ED9216A412 for ; Wed, 25 Oct 2006 13:56:33 +0000 (UTC) (envelope-from kreios@gmail.com) Received: from wx-out-0506.google.com (wx-out-0506.google.com [66.249.82.233]) by mx1.FreeBSD.org (Postfix) with ESMTP id E60BF43D5E for ; Wed, 25 Oct 2006 13:56:30 +0000 (GMT) (envelope-from kreios@gmail.com) Received: by wx-out-0506.google.com with SMTP id i27so109750wxd for ; Wed, 25 Oct 2006 06:56:30 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:in-reply-to:references:mime-version:content-type:message-id:cc:content-transfer-encoding:from:subject:date:to:x-mailer; b=EMmuZJcCBhsmJlvL1DG8iBv8+UX135gu2cZedmWpHMy71p5rF8sxndt6pbQc/TWhpgfROKbtCJRd6O28+0kNc1g7lKp0pJkioNAXF7EYgU9xwi6sbFK8QAnMeDwesYYnySEuPadDM3aqDcqVgD0QUQ991bUMjPRE1HAua19CfpQ= Received: by 10.90.31.19 with SMTP id e19mr194141age; Wed, 25 Oct 2006 06:56:30 -0700 (PDT) Received: from ?192.168.1.198? ( [71.113.235.243]) by mx.google.com with ESMTP id 29sm1372479wrl.2006.10.25.06.56.28; Wed, 25 Oct 2006 06:56:29 -0700 (PDT) In-Reply-To: References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Dave Date: Wed, 25 Oct 2006 08:56:27 -0500 To: gnn@freebsd.org X-Mailer: Apple Mail (2.752.2) Cc: performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 13:56:33 -0000 On Oct 25, 2006, at 4:50 AM, gnn@freebsd.org wrote: > At Tue, 24 Oct 2006 21:59:57 -0500, > kreios@gmail.com wrote: >> >> I am running some performance tests on named to see how it performs >> with different configurations on FreeBSD and figured I would share >> the >> first results. The first tests are for serving up static data. > > Thanks very much for this! > > Can we possible see a dmesg output as well, just for completeness? Here you go: Copyright (c) 1992-2006 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD is a registered trademark of The FreeBSD Foundation. FreeBSD 7.0-CURRENT #1: Wed Oct 25 13:39:34 UTC 2006 root@dnstest2.net.tamu.edu:/usr/obj/usr/src/sys/GENERIC Timecounter "i8254" frequency 1193182 Hz quality 0 CPU: Intel(R) Pentium(R) D CPU 3.40GHz (3391.52-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0xf62 Stepping = 2 Features=0xbfebfbff Features2=0xe43d> AMD Features=0x20100000 AMD Features2=0x1 Cores per package: 2 real memory = 1072562176 (1022 MB) avail memory = 1040306176 (992 MB) ACPI APIC Table: FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs cpu0 (BSP): APIC ID: 0 cpu1 (AP): APIC ID: 1 ioapic0 irqs 0-23 on motherboard ioapic1 irqs 24-47 on motherboard kbd1 at kbdmux0 ath_hal: 0.9.17.2 (AR5210, AR5211, AR5212, RF5111, RF5112, RF2413, RF5413) acpi0: on motherboard acpi0: Power Button (fixed) Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 acpi_timer0: <24-bit timer at 3.579545MHz> port 0x1008-0x100b on acpi0 cpu0: on acpi0 acpi_throttle0: on cpu0 cpu1: on acpi0 acpi_throttle1: on cpu1 acpi_throttle1: failed to attach P_CNT device_attach: acpi_throttle1 attach returned 6 pcib0: port 0xcf8-0xcff on acpi0 pci0: on pcib0 pcib1: irq 16 at device 1.0 on pci0 pci1: on pcib1 pcib2: irq 17 at device 28.0 on pci0 pci2: on pcib2 pcib3: at device 0.0 on pci2 pci3: on pcib3 pci2: at device 0.1 (no driver attached) pcib4: irq 17 at device 28.4 on pci0 pci4: on pcib4 em0: port 0x4000-0x401f mem 0xed200000-0xed21ffff irq 16 at device 0.0 on pci4 em0: Ethernet address: 00:30:48:55:df:e2 pcib5: irq 16 at device 28.5 on pci0 pci5: on pcib5 em1: port 0x5000-0x501f mem 0xed300000-0xed31ffff irq 17 at device 0.0 on pci5 em1: Ethernet address: 00:30:48:55:df:e3 uhci0: port 0x3000-0x301f irq 23 at device 29.0 on pci0 uhci0: [GIANT-LOCKED] usb0: on uhci0 usb0: USB revision 1.0 uhub0: on usb0 uhub0: 2 ports with 2 removable, self powered uhci1: port 0x3020-0x303f irq 19 at device 29.1 on pci0 uhci1: [GIANT-LOCKED] usb1: on uhci1 usb1: USB revision 1.0 uhub1: on usb1 uhub1: 2 ports with 2 removable, self powered uhci2: port 0x3040-0x305f irq 18 at device 29.2 on pci0 uhci2: [GIANT-LOCKED] usb2: on uhci2 usb2: USB revision 1.0 uhub2: on usb2 uhub2: 2 ports with 2 removable, self powered uhci3: port 0x3060-0x307f irq 16 at device 29.3 on pci0 uhci3: [GIANT-LOCKED] usb3: on uhci3 usb3: USB revision 1.0 uhub3: on usb3 uhub3: 2 ports with 2 removable, self powered ehci0: mem 0xed000000-0xed0003ff irq 23 at device 29.7 on pci0 ehci0: [GIANT-LOCKED] usb4: EHCI version 1.0 usb4: companion controllers, 2 ports each: usb0 usb1 usb2 usb3 usb4: on ehci0 usb4: USB revision 2.0 uhub4: on usb4 uhub4: 8 ports with 8 removable, self powered pcib6: at device 30.0 on pci0 pci10: on pcib6 vgapci0: port 0x6000-0x60ff mem 0xee000000-0xeeffffff,0xed400000-0xed400fff irq 16 at device 0.0 on pci10 isab0: at device 31.0 on pci0 isa0: on isab0 atapci0: port 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0x30b0-0x30bf at device 31.2 on pci0 ata0: on atapci0 ata1: on atapci0 pci0: at device 31.3 (no driver attached) acpi_button0: on acpi0 atkbdc0: port 0x60,0x64 irq 1 on acpi0 atkbd0: irq 1 on atkbdc0 kbd0 at atkbd0 atkbd0: [GIANT-LOCKED] psm0: irq 12 on atkbdc0 psm0: [GIANT-LOCKED] psm0: model IntelliMouse Explorer, device ID 4 sio0: <16550A-compatible COM port> port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 sio0: type 16550A sio0: [FAST] sio1: <16550A-compatible COM port> port 0x2f8-0x2ff irq 3 on acpi0 sio1: type 16550A sio1: [FAST] fdc0: port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on acpi0 fdc0: [FAST] pmtimer0 on isa0 orm0: at iomem 0xc0000-0xc7fff,0xc8000-0xc8fff, 0xc9000-0xc9fff pnpid ORM0000 on isa0 ppc0: at port 0x378-0x37f irq 7 on isa0 ppc0: SMC-like chipset (ECP/EPP/PS2/NIBBLE) in COMPATIBLE mode ppc0: FIFO with 16/16/9 bytes threshold ppbus0: on ppc0 plip0: on ppbus0 lpt0: on ppbus0 lpt0: Interrupt-driven port ppi0: on ppbus0 ppc0: [GIANT-LOCKED] sc0: at flags 0x100 on isa0 sc0: VGA <16 virtual consoles, flags=0x300> vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 Timecounters tick every 1.000 msec ad0: 76319MB at ata0-master SATA150 acd0: CDROM at ata1-master UDMA33 SMP: AP CPU #1 Launched! Trying to mount root from ufs:/dev/ad0s1a -- Dave From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 13:58:51 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id EB00916A417 for ; Wed, 25 Oct 2006 13:58:50 +0000 (UTC) (envelope-from kreios@gmail.com) Received: from wx-out-0506.google.com (wx-out-0506.google.com [66.249.82.228]) by mx1.FreeBSD.org (Postfix) with ESMTP id B16A543D83 for ; Wed, 25 Oct 2006 13:58:31 +0000 (GMT) (envelope-from kreios@gmail.com) Received: by wx-out-0506.google.com with SMTP id i27so110353wxd for ; Wed, 25 Oct 2006 06:58:31 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:mime-version:in-reply-to:references:content-type:message-id:content-transfer-encoding:from:subject:date:to:x-mailer; b=MYn0ZrNRirvrDrQFLB8obZ5oaXYnud1HW3T8cz81+fDyl5kPyXUwd/Te9OtZL48nyaiccetRsJ167rCle+Cy05Y6t0Ogo7/fnZQL3MrHPLoBjzgWzz9OEwX1dm2jYsNZWYphVyr+0nDe/QW+3wqWY1uYF4LbpQSyOS4518P/X8U= Received: by 10.90.52.18 with SMTP id z18mr196423agz; Wed, 25 Oct 2006 06:58:31 -0700 (PDT) Received: from ?192.168.1.198? ( [71.113.235.243]) by mx.google.com with ESMTP id e19sm2795629qba.2006.10.25.06.58.29; Wed, 25 Oct 2006 06:58:30 -0700 (PDT) Mime-Version: 1.0 (Apple Message framework v752.2) In-Reply-To: References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Dave Date: Wed, 25 Oct 2006 08:58:27 -0500 To: performance@freebsd.org X-Mailer: Apple Mail (2.752.2) Cc: Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 13:58:51 -0000 On Oct 25, 2006, at 4:50 AM, gnn@freebsd.org wrote: > At Tue, 24 Oct 2006 21:59:57 -0500, > kreios@gmail.com wrote: >> >> I am running some performance tests on named to see how it performs >> with different configurations on FreeBSD and figured I would share >> the >> first results. The first tests are for serving up static data. > > Thanks very much for this! > > Can we possible see a dmesg output as well, just for completeness? Here you go: Copyright (c) 1992-2006 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD is a registered trademark of The FreeBSD Foundation. FreeBSD 7.0-CURRENT #1: Wed Oct 25 13:39:34 UTC 2006 root@dnstest2.net.tamu.edu:/usr/obj/usr/src/sys/GENERIC Timecounter "i8254" frequency 1193182 Hz quality 0 CPU: Intel(R) Pentium(R) D CPU 3.40GHz (3391.52-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0xf62 Stepping = 2 Features=0xbfebfbff Features2=0xe43d> AMD Features=0x20100000 AMD Features2=0x1 Cores per package: 2 real memory = 1072562176 (1022 MB) avail memory = 1040306176 (992 MB) ACPI APIC Table: FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs cpu0 (BSP): APIC ID: 0 cpu1 (AP): APIC ID: 1 ioapic0 irqs 0-23 on motherboard ioapic1 irqs 24-47 on motherboard kbd1 at kbdmux0 ath_hal: 0.9.17.2 (AR5210, AR5211, AR5212, RF5111, RF5112, RF2413, RF5413) acpi0: on motherboard acpi0: Power Button (fixed) Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 acpi_timer0: <24-bit timer at 3.579545MHz> port 0x1008-0x100b on acpi0 cpu0: on acpi0 acpi_throttle0: on cpu0 cpu1: on acpi0 acpi_throttle1: on cpu1 acpi_throttle1: failed to attach P_CNT device_attach: acpi_throttle1 attach returned 6 pcib0: port 0xcf8-0xcff on acpi0 pci0: on pcib0 pcib1: irq 16 at device 1.0 on pci0 pci1: on pcib1 pcib2: irq 17 at device 28.0 on pci0 pci2: on pcib2 pcib3: at device 0.0 on pci2 pci3: on pcib3 pci2: at device 0.1 (no driver attached) pcib4: irq 17 at device 28.4 on pci0 pci4: on pcib4 em0: port 0x4000-0x401f mem 0xed200000-0xed21ffff irq 16 at device 0.0 on pci4 em0: Ethernet address: 00:30:48:55:df:e2 pcib5: irq 16 at device 28.5 on pci0 pci5: on pcib5 em1: port 0x5000-0x501f mem 0xed300000-0xed31ffff irq 17 at device 0.0 on pci5 em1: Ethernet address: 00:30:48:55:df:e3 uhci0: port 0x3000-0x301f irq 23 at device 29.0 on pci0 uhci0: [GIANT-LOCKED] usb0: on uhci0 usb0: USB revision 1.0 uhub0: on usb0 uhub0: 2 ports with 2 removable, self powered uhci1: port 0x3020-0x303f irq 19 at device 29.1 on pci0 uhci1: [GIANT-LOCKED] usb1: on uhci1 usb1: USB revision 1.0 uhub1: on usb1 uhub1: 2 ports with 2 removable, self powered uhci2: port 0x3040-0x305f irq 18 at device 29.2 on pci0 uhci2: [GIANT-LOCKED] usb2: on uhci2 usb2: USB revision 1.0 uhub2: on usb2 uhub2: 2 ports with 2 removable, self powered uhci3: port 0x3060-0x307f irq 16 at device 29.3 on pci0 uhci3: [GIANT-LOCKED] usb3: on uhci3 usb3: USB revision 1.0 uhub3: on usb3 uhub3: 2 ports with 2 removable, self powered ehci0: mem 0xed000000-0xed0003ff irq 23 at device 29.7 on pci0 ehci0: [GIANT-LOCKED] usb4: EHCI version 1.0 usb4: companion controllers, 2 ports each: usb0 usb1 usb2 usb3 usb4: on ehci0 usb4: USB revision 2.0 uhub4: on usb4 uhub4: 8 ports with 8 removable, self powered pcib6: at device 30.0 on pci0 pci10: on pcib6 vgapci0: port 0x6000-0x60ff mem 0xee000000-0xeeffffff,0xed400000-0xed400fff irq 16 at device 0.0 on pci10 isab0: at device 31.0 on pci0 isa0: on isab0 atapci0: port 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0x30b0-0x30bf at device 31.2 on pci0 ata0: on atapci0 ata1: on atapci0 pci0: at device 31.3 (no driver attached) acpi_button0: on acpi0 atkbdc0: port 0x60,0x64 irq 1 on acpi0 atkbd0: irq 1 on atkbdc0 kbd0 at atkbd0 atkbd0: [GIANT-LOCKED] psm0: irq 12 on atkbdc0 psm0: [GIANT-LOCKED] psm0: model IntelliMouse Explorer, device ID 4 sio0: <16550A-compatible COM port> port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 sio0: type 16550A sio0: [FAST] sio1: <16550A-compatible COM port> port 0x2f8-0x2ff irq 3 on acpi0 sio1: type 16550A sio1: [FAST] fdc0: port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on acpi0 fdc0: [FAST] pmtimer0 on isa0 orm0: at iomem 0xc0000-0xc7fff,0xc8000-0xc8fff, 0xc9000-0xc9fff pnpid ORM0000 on isa0 ppc0: at port 0x378-0x37f irq 7 on isa0 ppc0: SMC-like chipset (ECP/EPP/PS2/NIBBLE) in COMPATIBLE mode ppc0: FIFO with 16/16/9 bytes threshold ppbus0: on ppc0 plip0: on ppbus0 lpt0: on ppbus0 lpt0: Interrupt-driven port ppi0: on ppbus0 ppc0: [GIANT-LOCKED] sc0: at flags 0x100 on isa0 sc0: VGA <16 virtual consoles, flags=0x300> vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 Timecounters tick every 1.000 msec ad0: 76319MB at ata0-master SATA150 acd0: CDROM at ata1-master UDMA33 SMP: AP CPU #1 Launched! Trying to mount root from ufs:/dev/ad0s1a -- Dave From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 14:04:13 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A51DC16A412; Wed, 25 Oct 2006 14:04:13 +0000 (UTC) (envelope-from kris@obsecurity.org) Received: from elvis.mu.org (elvis.mu.org [192.203.228.196]) by mx1.FreeBSD.org (Postfix) with ESMTP id 94C5E43E17; Wed, 25 Oct 2006 14:03:40 +0000 (GMT) (envelope-from kris@obsecurity.org) Received: from obsecurity.dyndns.org (elvis.mu.org [192.203.228.196]) by elvis.mu.org (Postfix) with ESMTP id E94BE1A4D84; Wed, 25 Oct 2006 07:03:30 -0700 (PDT) Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id BE28D5144E; Wed, 25 Oct 2006 10:03:27 -0400 (EDT) Date: Wed, 25 Oct 2006 10:03:27 -0400 From: Kris Kennaway To: Dave Message-ID: <20061025140327.GA31484@xor.obsecurity.org> References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="TB36FDmn/VVEgNH/" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.2i Cc: gnn@freebsd.org, performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 14:04:13 -0000 --TB36FDmn/VVEgNH/ Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed, Oct 25, 2006 at 08:56:27AM -0500, Dave wrote: > On Oct 25, 2006, at 4:50 AM, gnn@freebsd.org wrote: >=20 > >At Tue, 24 Oct 2006 21:59:57 -0500, > >kreios@gmail.com wrote: > >> > >>I am running some performance tests on named to see how it performs > >>with different configurations on FreeBSD and figured I would share =20 > >>the > >>first results. The first tests are for serving up static data. > > > >Thanks very much for this! > > > >Can we possible see a dmesg output as well, just for completeness? >=20 > Here you go: There are a couple of things you could try to increase performance - they're probably all documented on the mysql tuning page. One thing you could do would be to set: kern.timecounter.choice=3DTSC kern.timecounter.smp_tsc=3D1 which is usually an optimization on the machines where the hardware supports it. I'd be interested in measuring and optimizing for this workload but I have no idea how to set it up (my time is also limited for the next few weeks). If you're interested in e.g. giving me access to your test setup then we could try to work something out. Kris --TB36FDmn/VVEgNH/ Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (FreeBSD) iD8DBQFFP26vWry0BWjoQKURAg8RAKDQ6MMo20zJeE8807+Hko51TD5TwQCfXcDw Ap+0O4ELVth+HlpWHPzKk2Y= =fsCL -----END PGP SIGNATURE----- --TB36FDmn/VVEgNH/-- From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 15:56:44 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 55BBF16A54E for ; Wed, 25 Oct 2006 15:56:44 +0000 (UTC) (envelope-from kreios@gmail.com) Received: from nz-out-0102.google.com (nz-out-0102.google.com [64.233.162.205]) by mx1.FreeBSD.org (Postfix) with ESMTP id CC9BC43D53 for ; Wed, 25 Oct 2006 15:56:43 +0000 (GMT) (envelope-from kreios@gmail.com) Received: by nz-out-0102.google.com with SMTP id o37so120554nzf for ; Wed, 25 Oct 2006 08:56:43 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:in-reply-to:references:mime-version:content-type:message-id:cc:content-transfer-encoding:from:subject:date:to:x-mailer; b=V0DWcN19nstuPxnRB5WEg+YXa3W3kigBdjay6mU4J67M8T05cqjhfQwGj/0FflSRVelWj3cXa2FQ3iLXriff8zWAJRvvILpeQViyaBtxGcini8GXdneWV2TYEJzMTAcee6lxzts2a1iREnGXJduX1W6obCrG1miyc9vmhK0SdLo= Received: by 10.65.54.9 with SMTP id g9mr1111641qbk; Wed, 25 Oct 2006 08:56:42 -0700 (PDT) Received: from ?192.168.1.198? ( [71.113.235.243]) by mx.google.com with ESMTP id f18sm2998784qba.2006.10.25.08.56.42; Wed, 25 Oct 2006 08:56:42 -0700 (PDT) In-Reply-To: <20061025073511.GA90244@stud.fit.vutbr.cz> References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> <20061025073511.GA90244@stud.fit.vutbr.cz> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Dave Date: Wed, 25 Oct 2006 10:56:40 -0500 To: Divacky Roman X-Mailer: Apple Mail (2.752.2) Cc: performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 15:56:44 -0000 On Oct 25, 2006, at 2:35 AM, Divacky Roman wrote: > On Tue, Oct 24, 2006 at 09:59:57PM -0500, kreios@gmail.com wrote: >> I am running some performance tests on named to see how it performs >> with different configurations on FreeBSD and figured I would share >> the >> first results. The first tests are for serving up static data. >> >> System: >> Supermicro PDSMi Motherboard >> 1G Memory >> Intel Pentium D CPU 3.40GHz >> Intel Gigibit NIC >> Bind 9.2.3 >> >> OS UP UP+P MP MP+P MP+TP MP+TT MP >> +TP+P >> MP+TT+P >> --------------------------------------------------------------------- >> ---------- >> FreeBSD 4.11 28455 28370 28976 X X X >> X X >> FreeBSD 6.1 29074 34260 34635 35730 17846 38780 19776 >> 44188 >> FreeBSD Stable 30190 34707 33294 36651 18893 39374 19449 >> 44169 >> FreeBSD Current 30707 34029 32300 33689 15535 40554 13886 >> 42071 >> Ubuntu 6.06 X X X X X 37294 >> X X > > I see regression between -current and -stable. are you sure you > tested without > any debuging stuff? some performance speedups went in in 7-current I would attribute the regression to my testing setup. Running a couple of the tests again, I get numbers more in line with stable and release. In addition, I was probably not as careful with current as we will not be running it in production. I will see if I can find the time to run the numbers again and update the table. FYI, this first round of testing was to answer the question, does using threaded bind help performance on FreeBSD? In this minimal test case, it does. With the above info, I can now look into how a bind vs threaded bind performs in different test cases. This also gives me information on what I will gain/lose when deciding on various administration issues. > also - do you use the same config everywhere? -current GENERIC > doesnt have COMPAT_43 > for example which miht affect performance (additional locking) etc. I modified the kernel configuration files that where included with the distribution. For release, stable and current, I created four kernels; uni-processor, uni-processor with polling, multi-processor, multi- processor with polling. The OS was as default as possible. For this test, I didn't want to make many changes. -- Dave From owner-freebsd-performance@FreeBSD.ORG Wed Oct 25 16:28:33 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id EA50216A4E7 for ; Wed, 25 Oct 2006 16:28:33 +0000 (UTC) (envelope-from kreios@gmail.com) Received: from nz-out-0102.google.com (nz-out-0102.google.com [64.233.162.202]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7E9BB43EF6 for ; Wed, 25 Oct 2006 16:25:37 +0000 (GMT) (envelope-from kreios@gmail.com) Received: by nz-out-0102.google.com with SMTP id o37so127254nzf for ; Wed, 25 Oct 2006 09:25:17 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:in-reply-to:references:mime-version:content-type:message-id:cc:content-transfer-encoding:from:subject:date:to:x-mailer; b=oCiB4m53ypKxXI4RTqpHYTlvbf/4KOWwE7NTqt2nDqr8oFd3GT1hqZM0LOgqJKKZ3K/DYZtaOHzjbsejBFd8nnNRbzP6cLr21A0Iaz0ft1HzH16drGkZQXZ55nx0LXK8vGu8gTJ+uEFj3ubwISmO1sK45yIZ9+M+r+E/UwZcd9o= Received: by 10.65.193.16 with SMTP id v16mr1173385qbp; Wed, 25 Oct 2006 09:25:16 -0700 (PDT) Received: from ?192.168.1.198? ( [71.113.235.243]) by mx.google.com with ESMTP id f14sm745098qba.2006.10.25.09.25.15; Wed, 25 Oct 2006 09:25:16 -0700 (PDT) In-Reply-To: <20061025140327.GA31484@xor.obsecurity.org> References: <2de4f2a00610241959l7a96ed59je79fb3e978f2c3d9@mail.gmail.com> <20061025140327.GA31484@xor.obsecurity.org> Mime-Version: 1.0 (Apple Message framework v752.2) Content-Type: text/plain; charset=US-ASCII; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Dave Date: Wed, 25 Oct 2006 11:25:12 -0500 To: Kris Kennaway X-Mailer: Apple Mail (2.752.2) Cc: gnn@freebsd.org, performance@freebsd.org Subject: Re: DNS Performance Numbers X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Oct 2006 16:28:34 -0000 On Oct 25, 2006, at 9:03 AM, Kris Kennaway wrote: > On Wed, Oct 25, 2006 at 08:56:27AM -0500, Dave wrote: >> On Oct 25, 2006, at 4:50 AM, gnn@freebsd.org wrote: >> >>> At Tue, 24 Oct 2006 21:59:57 -0500, >>> kreios@gmail.com wrote: >>>> >>>> I am running some performance tests on named to see how it performs >>>> with different configurations on FreeBSD and figured I would share >>>> the >>>> first results. The first tests are for serving up static data. >>> >>> Thanks very much for this! >>> >>> Can we possible see a dmesg output as well, just for completeness? >> >> Here you go: > > There are a couple of things you could try to increase performance - > they're probably all documented on the mysql tuning page. One thing > you could do would be to set: > > kern.timecounter.choice=TSC > kern.timecounter.smp_tsc=1 > > which is usually an optimization on the machines where the hardware > supports it. In my case, it was performance went down slightly. I have played with some of Robert Watson's time patches and I do see a small boost (44786 -> 45179). > I'd be interested in measuring and optimizing for this workload but I > have no idea how to set it up (my time is also limited for the next > few weeks). If you're interested in e.g. giving me access to your > test setup then we could try to work something out. I might take you up on that offer when I have a few cycles but that will be at least a few weeks. :( -- Dave From owner-freebsd-performance@FreeBSD.ORG Fri Oct 27 21:34:26 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0E74916A415 for ; Fri, 27 Oct 2006 21:34:26 +0000 (UTC) (envelope-from cracauer@koef.zs64.net) Received: from koef.zs64.net (koef.zs64.net [212.12.50.230]) by mx1.FreeBSD.org (Postfix) with ESMTP id 417E443D4C for ; Fri, 27 Oct 2006 21:34:25 +0000 (GMT) (envelope-from cracauer@koef.zs64.net) Received: from koef.zs64.net (koef.zs64.net [212.12.50.230]) by koef.zs64.net (8.13.8/8.13.8) with ESMTP id k9RLYNWw086941; Fri, 27 Oct 2006 23:34:23 +0200 (CEST) (envelope-from cracauer@koef.zs64.net) Received: (from cracauer@localhost) by koef.zs64.net (8.13.8/8.13.8/Submit) id k9RLYM6v086937; Fri, 27 Oct 2006 17:34:22 -0400 (EDT) (envelope-from cracauer) Date: Fri, 27 Oct 2006 17:34:22 -0400 From: Martin Cracauer To: NOC Meganet , freebsd-performance@freebsd.org Message-ID: <20061027213422.GA86642@cons.org> References: <20061014130331.68863.qmail@web33312.mail.mud.yahoo.com> <200610141313.28868.tec@mega.net.br> <20061014180518.GA75972@Geeks.ORG> <200610150045.42927.tec@mega.net.br> <20061015144638.GB98831@Geeks.ORG> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20061015144638.GB98831@Geeks.ORG> User-Agent: Mutt/1.4.2.2i Cc: Subject: Re: Performance 4.x vs. 6.x X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 Oct 2006 21:34:26 -0000 Wasn't Dragonfly split off to do exactly what some troll here wanted? Use FreeBSD-4.x as a base for a *BSD. I would be curious to know whether Dragonfly-current or whatever they name it fix the performance problems assumed (but not proven). Or whether Dragonfly went into difficulties with thread libraries, API details and new hardware idioticy, too. Makes you wonder why none of the commerical vendors that did not change to FreeBSD-6 didn't change to Dragonfly either. BTW, if you want to see how professional SATA-II is just turn the write cache on the drive off (as you theoretically must to ensure data integrety) and try the same on SCSI. I actually don't understand the reason but under SCSI you lose 20% or somesuch write performance, under SATA you lose 90+%. > > > > I had no time to test it on a life webserver and probably can't do > > > > it so soon but I tell you that a 10K Raptor is faster then a 15K > > > > 320Mb SCSI when compiling world or untarring large files. Also NCQ > > > > is not reserved to SCSI anymore so when you see the price then it is > > > > becoming a valid option for small servers. NCQ is not working for many common SATA controller drivers under Linux or FreeBSD, most notably NForce (unless that changed recently). The reason why the SCSI disk is so slow is most likely that your controller has a FreeBSD driver which is giant-locked. `make world` without "-j" doesn't really stress the harddrive's seeking, which is where the faster SCSI disk would shine. For just linear accesses SCSI is actually very disappointing these days. Martin -- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Martin Cracauer http://www.cons.org/cracauer/ FreeBSD - where you want to go, today. http://www.freebsd.org/ From owner-freebsd-performance@FreeBSD.ORG Fri Oct 27 23:04:00 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 20F5316A407 for ; Fri, 27 Oct 2006 23:04:00 +0000 (UTC) (envelope-from stevep-hv@zpfe.com) Received: from mail.zpfe.com (mail.zpfe.com [208.42.168.33]) by mx1.FreeBSD.org (Postfix) with SMTP id 7D7F843D58 for ; Fri, 27 Oct 2006 23:03:59 +0000 (GMT) (envelope-from stevep-hv@zpfe.com) Received: (qmail 46722 invoked from network); 27 Oct 2006 23:03:58 -0000 Received: from unknown (HELO revere.zpfe.com) (208.42.168.33) by mail.zpfe.com with SMTP; 27 Oct 2006 23:03:58 -0000 Message-Id: <6.2.3.4.0.20061027180329.020bed68@localhost> X-Mailer: QUALCOMM Windows Eudora Version 6.2.3.4 Date: Fri, 27 Oct 2006 18:03:33 -0500 To: performance@freebsd.org From: Steve Peterson Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII"; format=flowed Cc: Subject: gvinum raid5 performance seems slow X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 Oct 2006 23:04:00 -0000 I recently set up a media server for home use and decided to try the gvinum raid5 support to learn about it and see how it performs. It seems slower than I'd expect -- a little under 6MB/second, with about 50 IOs/drive/second -- and I'm trying to understand why. Any assistance/pointers would be appreciated. The disk system consists of 4 Seagate NL35 SATA ST3250623NS drives connected to a Promise TX4300 (PDC40719) controller, organized as a RAID5 volume via gvinum using this configuration: drive drive01 device /dev/ad10 drive drive02 device /dev/ad6 drive drive03 device /dev/ad4 drive drive04 device /dev/ad8 volume vol1 plex org raid5 256k sd length 200001m drive drive01 sd length 200001m drive drive02 sd length 200001m drive drive03 sd length 200001m drive drive04 dd reports the following performance on a 1G file write to the RAID5 hosted volume: $ time dd if=/dev/zero of=big.file bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 179.717742 secs (5834571 bytes/sec) 179.76 real 0.02 user 16.60 sys By comparison, creating the same file on the system disk (an old ATA ST380021A connected via a SIS 730 on the motherboard): time dd if=/dev/zero of=big.file bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 28.264056 secs (37099275 bytes/sec) 28.32 real 0.01 user 19.13 sys and vmstat reports about 280-300 IOs/second to that drive. The CPU is pretty weak -- an Athlon 750. Is that the source of my problem? If you look at the vmstat output below the machine is busy but not pegged. $ vmstat -n 5 1 procs memory page disks faults cpu r b w avm fre flt re pi po fr sr ad0 ad4 ad6 ad8 ad10 in sy cs us sy id 1 0 0 96700 134124 19 3 0 0 65 12 0 0 0 0 0 1375 239 621 1 1 98 0 0 0 96700 134124 2 0 0 0 0 0 0 0 0 0 0 1305 180 445 2 0 98 0 0 0 96700 134124 0 0 0 0 0 0 0 0 0 0 0 1302 201 449 1 1 98 0 0 0 96700 134124 0 0 0 0 0 0 0 0 0 0 0 1353 165 545 1 1 98 1 0 0 99088 129828 311 0 0 0 1328 0 0 14 24 23 13 1448 310 1286 0 18 82 0 1 0 99088 120228 0 0 0 0 5088 0 0 56 48 48 56 1686 187 2794 0 64 36 0 1 0 99088 114212 0 0 0 0 4992 0 0 54 50 52 48 1659 184 2694 2 54 44 0 1 0 99088 107044 0 0 0 0 5088 0 0 50 51 57 50 1670 188 2777 2 56 42 0 1 0 99088 101668 0 0 0 0 5184 0 0 51 58 52 51 1678 190 2801 1 56 43 0 1 0 99088 95140 0 0 0 0 4896 0 1 48 52 48 52 1662 186 2665 1 57 42 0 1 0 99088 88356 0 0 0 0 4896 0 0 50 47 50 53 1648 184 2641 1 54 45 0 1 0 99088 81316 0 0 0 0 4800 0 0 52 48 48 53 1620 184 2602 0 57 43 0 1 0 99088 73892 0 0 0 0 4992 0 0 54 50 49 46 1685 191 2698 1 62 37 0 1 0 99088 68260 0 0 0 0 4992 0 0 48 50 54 51 1661 184 2663 1 56 43 0 1 0 99088 61032 0 0 0 0 5088 0 0 51 53 53 51 1656 186 2735 1 57 42 0 1 0 99088 54436 0 0 0 0 4768 0 0 48 50 50 47 1637 184 2580 0 56 44 0 1 0 99088 48292 0 0 0 0 5120 0 2 50 55 49 53 1647 186 2710 1 62 38 0 1 0 99088 42020 0 0 0 0 4928 0 0 53 47 49 55 1657 192 2671 1 58 41 0 1 0 99088 35492 0 0 0 0 4768 0 0 50 48 47 49 1639 181 2544 0 59 41 0 1 0 99088 28836 0 0 0 0 4996 0 2 54 50 52 48 1654 186 2689 0 57 43 0 1 0 99088 21540 0 0 0 0 4704 0 0 47 47 49 49 1648 184 2580 2 58 40 0 1 0 99088 14756 0 0 0 0 4928 0 5 49 51 54 48 1638 184 2645 1 58 41 0 1 0 99088 10276 0 0 0 0 4864 0 0 48 49 48 49 1679 196 2662 1 55 45 0 1 0 99088 10152 0 0 0 0 4800 1937 0 47 51 50 48 1651 181 2637 1 58 42 1 1 0 99088 14560 0 6746 0 0 4948 9308 0 46 37 40 49 1616 176 2396 1 57 42 0 1 0 99088 15336 0 9815 0 0 5328 11178 0 61 64 59 67 1612 188 2741 0 62 38 0 1 0 99088 15532 0 6188 0 0 5536 7452 0 49 49 57 38 1618 190 2526 1 61 38 1 0 0 99088 12012 0 3054 0 0 5728 3726 0 69 63 67 61 1637 189 2859 2 58 41 0 1 0 99088 15532 0 12692 0 0 5700 14904 1 55 49 53 57 1640 183 2677 0 58 42 0 1 0 99088 9388 0 0 0 0 5696 0 0 65 62 61 66 1600 184 2699 1 61 38 0 1 0 99088 14828 0 2925 0 0 5328 5565 0 64 68 57 65 1602 194 2758 1 53 46 0 1 0 99088 13100 0 2718 0 0 5904 3726 0 50 52 53 55 1594 184 2556 1 59 40 0 1 0 99088 14508 0 13368 0 0 5984 14904 0 64 66 61 70 1642 184 2901 2 63 36 0 1 0 99088 13608 0 0 0 0 5888 1855 0 65 71 71 65 1630 177 2849 1 63 36 0 1 0 99088 13932 0 10265 0 0 5728 11178 0 62 64 63 51 1633 176 2742 1 60 39 configuration from last boot: Sep 24 12:11:35 archive kernel: Copyright (c) 1992-2006 The FreeBSD Project. Sep 24 12:11:35 archive kernel: Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 Sep 24 12:11:35 archive kernel: The Regents of the University of California. All rights reserved. Sep 24 12:11:35 archive kernel: FreeBSD 6.1-RELEASE-p7 #5: Wed Sep 20 14:03:56 CDT 2006 Sep 24 12:11:35 archive kernel: root@archive.zpfe.com:/usr/obj/usr/src/sys/ARCHIVE Sep 24 12:11:35 archive kernel: Timecounter "i8254" frequency 1193182 Hz quality 0 Sep 24 12:11:35 archive kernel: CPU: AMD Athlon(tm) Processor (746.67-MHz 686-class CPU) Sep 24 12:11:35 archive kernel: Origin = "AuthenticAMD" Id = 0x644 Stepping = 4 Sep 24 12:11:35 archive kernel: Features=0x183f9ff Sep 24 12:11:35 archive kernel: AMD Features=0xc0440800,MMX+,3DNow+,3DNow> Sep 24 12:11:35 archive kernel: real memory = 251592704 (239 MB) Sep 24 12:11:35 archive kernel: avail memory = 236695552 (225 MB) Sep 24 12:11:35 archive kernel: kbd1 at kbdmux0 Sep 24 12:11:35 archive kernel: acpi0: on motherboard Sep 24 12:11:35 archive kernel: acpi0: Power Button (fixed) Sep 24 12:11:35 archive kernel: Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 Sep 24 12:11:35 archive kernel: acpi_timer0: <24-bit timer at 3.579545MHz> port 0x5008-0x500b on acpi0 Sep 24 12:11:35 archive kernel: cpu0: on acpi0 Sep 24 12:11:35 archive kernel: acpi_throttle0: on cpu0 Sep 24 12:11:35 archive kernel: acpi_button0: on acpi0 Sep 24 12:11:35 archive kernel: pcib0: port 0xcf8-0xcff on acpi0 Sep 24 12:11:35 archive kernel: pci0: on pcib0 Sep 24 12:11:35 archive kernel: agp0: mem 0xd0000000-0xd3ffffff at device 0.0 on pci0 Sep 24 12:11:35 archive kernel: atapci0: port 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0xff00-0xff0f at device 0.1 on pci0 Sep 24 12:11:35 archive kernel: ata0: on atapci0 Sep 24 12:11:35 archive kernel: ata1: on atapci0 Sep 24 12:11:35 archive kernel: isab0: at device 1.0 on pci0 Sep 24 12:11:35 archive kernel: isa0: on isab0 Sep 24 12:11:35 archive kernel: sis0: port 0xd400-0xd4ff mem 0xcfff8000-0xcfff8fff irq 11 at device 1.1 on pci0 Sep 24 12:11:35 archive kernel: miibus0: on sis0 Sep 24 12:11:35 archive kernel: ukphy0: on miibus0 Sep 24 12:11:35 archive kernel: ukphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto Sep 24 12:11:35 archive kernel: sis0: Ethernet address: 00:0a:e6:14:e3:53 Sep 24 12:11:35 archive kernel: ohci0: mem 0xcfff9000-0xcfff9fff irq 10 at device 1.2 on pci0 Sep 24 12:11:35 archive kernel: ohci0: [GIANT-LOCKED] Sep 24 12:11:35 archive kernel: usb0: OHCI version 1.0, legacy support Sep 24 12:11:35 archive kernel: usb0: on ohci0 Sep 24 12:11:35 archive kernel: usb0: USB revision 1.0 Sep 24 12:11:35 archive kernel: uhub0: SiS OHCI root hub, class 9/0, rev 1.00/1.00, addr 1 Sep 24 12:11:35 archive kernel: uhub0: 3 ports with 3 removable, self powered Sep 24 12:11:35 archive kernel: ohci1: mem 0xcfffa000-0xcfffafff irq 10 at device 1.3 on pci0 Sep 24 12:11:35 archive kernel: ohci1: [GIANT-LOCKED] Sep 24 12:11:35 archive kernel: usb1: OHCI version 1.0, legacy support Sep 24 12:11:35 archive kernel: usb1: on ohci1 Sep 24 12:11:35 archive kernel: usb1: USB revision 1.0 Sep 24 12:11:35 archive kernel: uhub1: SiS OHCI root hub, class 9/0, rev 1.00/1.00, addr 1 Sep 24 12:11:35 archive kernel: uhub1: 3 ports with 3 removable, self powered Sep 24 12:11:35 archive kernel: pcib1: at device 2.0 on pci0 Sep 24 12:11:35 archive kernel: pci1: on pcib1 Sep 24 12:11:35 archive kernel: pci1: at device 0.0 (no driver attached) Sep 24 12:11:35 archive kernel: atapci1: port 0xdc00-0xdc7f,0xd800-0xd8ff mem 0xcfffb000-0xcfffbfff,0xcffc0000-0xcffdffff irq 11 at device 11.0 on pci0 Sep 24 12:11:35 archive kernel: ata2: on atapci1 Sep 24 12:11:35 archive kernel: ata3: on atapci1 Sep 24 12:11:35 archive kernel: ata4: on atapci1 Sep 24 12:11:35 archive kernel: ata5: on atapci1 Sep 24 12:11:35 archive kernel: acpi_button1: on acpi0 Sep 24 12:11:35 archive kernel: atkbdc0: port 0x60,0x64 irq 1 on acpi0 Sep 24 12:11:35 archive kernel: atkbd0: irq 1 on atkbdc0 Sep 24 12:11:35 archive kernel: atkbd0: irq 1 on atkbdc0 Sep 24 12:11:35 archive kernel: kbd0 at atkbd0 Sep 24 12:11:35 archive kernel: atkbd0: [GIANT-LOCKED] Sep 24 12:11:35 archive kernel: pmtimer0 on isa0 Sep 24 12:11:35 archive kernel: orm0: at iomem 0xc0000-0xcbfff,0xcc000-0xd57ff,0xd5800-0xdffff on isa0 Sep 24 12:11:35 archive kernel: ppc0: parallel port not found. Sep 24 12:11:35 archive kernel: sc0: at flags 0x100 on isa0 Sep 24 12:11:35 archive kernel: sc0: VGA <16 virtual consoles, flags=0x300> Sep 24 12:11:35 archive kernel: sio0: configured irq 4 not in bitmap of probed irqs 0 Sep 24 12:11:35 archive kernel: sio0: port may not be enabled Sep 24 12:11:35 archive kernel: sio0 at port 0x3f8-0x3ff irq 4 flags 0x10 on isa0 Sep 24 12:11:35 archive kernel: sio0: type 8250 or not responding Sep 24 12:11:35 archive kernel: sio1: configured irq 3 not in bitmap of probed irqs 0 Sep 24 12:11:35 archive kernel: sio1: port may not be enabled Sep 24 12:11:35 archive kernel: vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 Sep 24 12:11:35 archive kernel: Timecounter "TSC" frequency 746674414 Hz quality 800 Sep 24 12:11:35 archive kernel: Timecounters tick every 1.000 msec Sep 24 12:11:35 archive kernel: ad0: 76319MB at ata0-master UDMA100 Sep 24 12:11:35 archive kernel: acd0: CDROM at ata1-master PIO3 Sep 24 12:11:35 archive kernel: ad4: 238475MB at ata2-master SATA150 Sep 24 12:11:35 archive kernel: ad6: 238475MB at ata3-master SATA150 Sep 24 12:11:35 archive kernel: ad8: 238475MB at ata4-master SATA150 Sep 24 12:11:35 archive kernel: ad10: 238475MB at ata5-master SATA150 From owner-freebsd-performance@FreeBSD.ORG Sat Oct 28 04:15:04 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E6DFA16A403 for ; Sat, 28 Oct 2006 04:15:04 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh1.centtech.com (moat3.centtech.com [64.129.166.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7A82043D49 for ; Sat, 28 Oct 2006 04:15:04 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [192.168.42.25] ([192.168.42.25]) by mh1.centtech.com (8.13.8/8.13.8) with ESMTP id k9S4ExHl024948; Fri, 27 Oct 2006 23:15:02 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <4542D941.2070204@centtech.com> Date: Fri, 27 Oct 2006 23:14:57 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5.0.7 (X11/20061015) MIME-Version: 1.0 To: Steve Peterson References: <6.2.3.4.0.20061027180329.020bed68@localhost> In-Reply-To: <6.2.3.4.0.20061027180329.020bed68@localhost> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.88.4/2126/Fri Oct 27 08:48:55 2006 on mh1.centtech.com X-Virus-Status: Clean X-Spam-Status: No, score=-2.2 required=8.0 tests=AWL,BAYES_00 autolearn=ham version=3.1.6 X-Spam-Checker-Version: SpamAssassin 3.1.6 (2006-10-03) on mh1.centtech.com Cc: performance@freebsd.org Subject: Re: gvinum raid5 performance seems slow X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 28 Oct 2006 04:15:05 -0000 On 10/27/06 18:03, Steve Peterson wrote: > I recently set up a media server for home use and decided to try the > gvinum raid5 support to learn about it and see how it performs. It > seems slower than I'd expect -- a little under 6MB/second, with about > 50 IOs/drive/second -- and I'm trying to understand why. Any > assistance/pointers would be appreciated. > > The disk system consists of 4 Seagate NL35 SATA ST3250623NS drives > connected to a Promise TX4300 (PDC40719) controller, organized as a > RAID5 volume via gvinum using this configuration: > > drive drive01 device /dev/ad10 > drive drive02 device /dev/ad6 > drive drive03 device /dev/ad4 > drive drive04 device /dev/ad8 > > volume vol1 > plex org raid5 256k > sd length 200001m drive drive01 > sd length 200001m drive drive02 > sd length 200001m drive drive03 > sd length 200001m drive drive04 > > dd reports the following performance on a 1G file write to the RAID5 > hosted volume: > > $ time dd if=/dev/zero of=big.file bs=1m count=1000 > 1000+0 records in > 1000+0 records out > 1048576000 bytes transferred in 179.717742 secs (5834571 bytes/sec) > 179.76 real 0.02 user 16.60 sys > > By comparison, creating the same file on the system disk (an old ATA > ST380021A connected via a SIS 730 on the motherboard): > > time dd if=/dev/zero of=big.file bs=1m count=1000 > 1000+0 records in > 1000+0 records out > 1048576000 bytes transferred in 28.264056 secs (37099275 bytes/sec) > 28.32 real 0.01 user 19.13 sys > > and vmstat reports about 280-300 IOs/second to that drive. > > The CPU is pretty weak -- an Athlon 750. Is that the source of my > problem? If you look at the vmstat output below the machine is busy > but not pegged. Try the dd to the raw gvinum device instead of through a filesystem, and also to the individual disks. That will at least tell us where to look. Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Sat Oct 28 17:52:23 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 920EE16A494 for ; Sat, 28 Oct 2006 17:52:23 +0000 (UTC) (envelope-from stevep-hv@zpfe.com) Received: from mail.zpfe.com (mail.zpfe.com [208.42.168.33]) by mx1.FreeBSD.org (Postfix) with SMTP id B473443D5D for ; Sat, 28 Oct 2006 17:52:10 +0000 (GMT) (envelope-from stevep-hv@zpfe.com) Received: (qmail 92005 invoked from network); 28 Oct 2006 17:52:06 -0000 Received: from unknown (HELO revere.zpfe.com) (208.42.168.33) by mail.zpfe.com with SMTP; 28 Oct 2006 17:52:06 -0000 Message-Id: <6.2.3.4.0.20061028124559.02105930@localhost> X-Mailer: QUALCOMM Windows Eudora Version 6.2.3.4 Date: Sat, 28 Oct 2006 12:52:14 -0500 To: Eric Anderson ,performance@freebsd.org From: Steve Peterson In-Reply-To: <4542D941.2070204@centtech.com> References: <6.2.3.4.0.20061027180329.020bed68@localhost> <4542D941.2070204@centtech.com> Mime-Version: 1.0 Content-Type: text/plain; charset="US-ASCII"; format=flowed Cc: Subject: Re: gvinum raid5 performance seems slow X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 28 Oct 2006 17:52:23 -0000 Eric -- thanks for looking at my issue. Here's a dd reading from one of the disks underlying the array (the others have basically the same performance): $ time dd if=/dev/ad10 of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 15.322421 secs (68434095 bytes/sec) 0.008u 0.506s 0:15.33 3.2% 20+2715k 0+0io 0pf+0w and here's a dd reading from the raw gvinum device /dev/gvinum/vol1: $ time dd if=/dev/gvinum/vol1 of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 25.870684 secs (40531437 bytes/sec) 0.006u 0.552s 0:25.88 2.1% 23+3145k 0+0io 0pf+0w Is there a way to nondestructively write to the raw disk or gvinum device? For comparison, here's a read against the raw PATA device on the machine: $ time dd if=/dev/ad0 of=/dev/null bs=1m count=1000 1000+0 records in 1000+0 records out 1048576000 bytes transferred in 26.096070 secs (40181376 bytes/sec) 0.013u 0.538s 0:26.10 2.0% 24+3322k 0+0io 0pf+0w Steve At 11:14 PM 10/27/2006, Eric Anderson wrote: >On 10/27/06 18:03, Steve Peterson wrote: >>I recently set up a media server for home use and decided to try >>the gvinum raid5 support to learn about it and see how it >>performs. It seems slower than I'd expect -- a little under >>6MB/second, with about 50 IOs/drive/second -- and I'm trying to >>understand why. Any assistance/pointers would be appreciated. >>The disk system consists of 4 Seagate NL35 SATA ST3250623NS drives >>connected to a Promise TX4300 (PDC40719) controller, organized as a >>RAID5 volume via gvinum using this configuration: >>drive drive01 device /dev/ad10 >>drive drive02 device /dev/ad6 >>drive drive03 device /dev/ad4 >>drive drive04 device /dev/ad8 >>volume vol1 >> plex org raid5 256k >> sd length 200001m drive drive01 >> sd length 200001m drive drive02 >> sd length 200001m drive drive03 >> sd length 200001m drive drive04 >>dd reports the following performance on a 1G file write to the >>RAID5 hosted volume: >>$ time dd if=/dev/zero of=big.file bs=1m count=1000 >>1000+0 records in >>1000+0 records out >>1048576000 bytes transferred in 179.717742 secs (5834571 bytes/sec) >> 179.76 real 0.02 user 16.60 sys >>By comparison, creating the same file on the system disk (an old >>ATA ST380021A connected via a SIS 730 on the motherboard): >>time dd if=/dev/zero of=big.file bs=1m count=1000 >>1000+0 records in >>1000+0 records out >>1048576000 bytes transferred in 28.264056 secs (37099275 bytes/sec) >> 28.32 real 0.01 user 19.13 sys >>and vmstat reports about 280-300 IOs/second to that drive. >>The CPU is pretty weak -- an Athlon 750. Is that the source of my >>problem? If you look at the vmstat output below the machine is >>busy but not pegged. > > >Try the dd to the raw gvinum device instead of through a filesystem, >and also to the individual disks. That will at least tell us where to look. > > >Eric > > > >-- >------------------------------------------------------------------------ >Eric Anderson Sr. Systems Administrator Centaur Technology >Anything that works is better than anything that doesn't. >------------------------------------------------------------------------ >_______________________________________________ >freebsd-performance@freebsd.org mailing list >http://lists.freebsd.org/mailman/listinfo/freebsd-performance >To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Sat Oct 28 19:19:35 2006 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2DCA116A412 for ; Sat, 28 Oct 2006 19:19:35 +0000 (UTC) (envelope-from pete@he.iki.fi) Received: from silver.he.iki.fi (helenius.fi [193.64.42.241]) by mx1.FreeBSD.org (Postfix) with ESMTP id B618843D77 for ; Sat, 28 Oct 2006 19:19:26 +0000 (GMT) (envelope-from pete@he.iki.fi) Received: from localhost (localhost [127.0.0.1]) by silver.he.iki.fi (Postfix) with ESMTP id 17CBABBFF; Sat, 28 Oct 2006 22:19:24 +0300 (EEST) Received: from silver.he.iki.fi ([127.0.0.1]) by localhost (silver.he.iki.fi [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 7xTweE6ccyKo; Sat, 28 Oct 2006 22:19:17 +0300 (EEST) Received: from [IPv6:2001:670:84:0:dca1:af59:3d40:6dbd] (unknown [IPv6:2001:670:84:0:dca1:af59:3d40:6dbd]) by silver.he.iki.fi (Postfix) with ESMTP; Sat, 28 Oct 2006 22:19:16 +0300 (EEST) Message-ID: <4543AD35.30205@he.iki.fi> Date: Sat, 28 Oct 2006 22:19:17 +0300 From: Petri Helenius User-Agent: Thunderbird 1.5.0.7 (Windows/20060909) MIME-Version: 1.0 To: Steve Peterson References: <6.2.3.4.0.20061027180329.020bed68@localhost> <4542D941.2070204@centtech.com> <6.2.3.4.0.20061028124559.02105930@localhost> In-Reply-To: <6.2.3.4.0.20061028124559.02105930@localhost> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: performance@freebsd.org Subject: Re: gvinum raid5 performance seems slow X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 28 Oct 2006 19:19:35 -0000 According to my understanding vinum does not overlap requests to multiple disks when running in raid5 configuration so you're not going to achieve good numbers with just "single stream" tests. Pete Steve Peterson wrote: > Eric -- thanks for looking at my issue. Here's a dd reading from one > of the disks underlying the array (the others have basically the same > performance): > > $ time dd if=/dev/ad10 of=/dev/null bs=1m count=1000 > 1000+0 records in > 1000+0 records out > 1048576000 bytes transferred in 15.322421 secs (68434095 bytes/sec) > 0.008u 0.506s 0:15.33 3.2% 20+2715k 0+0io 0pf+0w > > and here's a dd reading from the raw gvinum device /dev/gvinum/vol1: > > $ time dd if=/dev/gvinum/vol1 of=/dev/null bs=1m count=1000 > 1000+0 records in > 1000+0 records out > 1048576000 bytes transferred in 25.870684 secs (40531437 bytes/sec) > 0.006u 0.552s 0:25.88 2.1% 23+3145k 0+0io 0pf+0w > > Is there a way to nondestructively write to the raw disk or gvinum > device? > > For comparison, here's a read against the raw PATA device on the machine: > > $ time dd if=/dev/ad0 of=/dev/null bs=1m count=1000 > 1000+0 records in > 1000+0 records out > 1048576000 bytes transferred in 26.096070 secs (40181376 bytes/sec) > 0.013u 0.538s 0:26.10 2.0% 24+3322k 0+0io 0pf+0w > > Steve > > > At 11:14 PM 10/27/2006, Eric Anderson wrote: >> On 10/27/06 18:03, Steve Peterson wrote: >>> I recently set up a media server for home use and decided to try the >>> gvinum raid5 support to learn about it and see how it performs. It >>> seems slower than I'd expect -- a little under 6MB/second, with >>> about 50 IOs/drive/second -- and I'm trying to understand why. Any >>> assistance/pointers would be appreciated. >>> The disk system consists of 4 Seagate NL35 SATA ST3250623NS drives >>> connected to a Promise TX4300 (PDC40719) controller, organized as a >>> RAID5 volume via gvinum using this configuration: >>> drive drive01 device /dev/ad10 >>> drive drive02 device /dev/ad6 >>> drive drive03 device /dev/ad4 >>> drive drive04 device /dev/ad8 >>> volume vol1 >>> plex org raid5 256k >>> sd length 200001m drive drive01 >>> sd length 200001m drive drive02 >>> sd length 200001m drive drive03 >>> sd length 200001m drive drive04 >>> dd reports the following performance on a 1G file write to the RAID5 >>> hosted volume: >>> $ time dd if=/dev/zero of=big.file bs=1m count=1000 >>> 1000+0 records in >>> 1000+0 records out >>> 1048576000 bytes transferred in 179.717742 secs (5834571 bytes/sec) >>> 179.76 real 0.02 user 16.60 sys >>> By comparison, creating the same file on the system disk (an old ATA >>> ST380021A connected via a SIS 730 on the motherboard): >>> time dd if=/dev/zero of=big.file bs=1m count=1000 >>> 1000+0 records in >>> 1000+0 records out >>> 1048576000 bytes transferred in 28.264056 secs (37099275 bytes/sec) >>> 28.32 real 0.01 user 19.13 sys >>> and vmstat reports about 280-300 IOs/second to that drive. >>> The CPU is pretty weak -- an Athlon 750. Is that the source of my >>> problem? If you look at the vmstat output below the machine is busy >>> but not pegged. >> >> >> Try the dd to the raw gvinum device instead of through a filesystem, >> and also to the individual disks. That will at least tell us where >> to look. >> >> >> Eric >> >> >> >> -- >> ------------------------------------------------------------------------ >> Eric Anderson Sr. Systems Administrator Centaur Technology >> Anything that works is better than anything that doesn't. >> ------------------------------------------------------------------------ >> _______________________________________________ >> freebsd-performance@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-performance >> To unsubscribe, send any mail to >> "freebsd-performance-unsubscribe@freebsd.org" > > > _______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to > "freebsd-performance-unsubscribe@freebsd.org" >