From owner-freebsd-performance@FreeBSD.ORG Sun Feb 18 21:13:00 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9C78C16A400 for ; Sun, 18 Feb 2007 21:13:00 +0000 (UTC) (envelope-from vdemart1@tin.it) Received: from smtp5.aruba.it (smtpd2.aruba.it [62.149.128.207]) by mx1.freebsd.org (Postfix) with SMTP id D2F5313C49D for ; Sun, 18 Feb 2007 21:12:59 +0000 (UTC) (envelope-from vdemart1@tin.it) Received: (qmail 28194 invoked by uid 89); 18 Feb 2007 20:46:17 -0000 Received: by simscan 1.1.0 ppid: 28181, pid: 28190, t: 0.0952s scanners: clamav: 0.88.4/m:40/d:1722 Received: from unknown (HELO ?10.155.100.8?) (82.55.234.173) by smtp5.aruba.it with SMTP; 18 Feb 2007 20:46:17 -0000 From: vittorio To: freebsd-performance@freebsd.org, freebsd-questions@freebsd.org Date: Sun, 18 Feb 2007 21:45:54 +0000 User-Agent: KMail/1.9.5 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200702182145.55275.vdemart1@tin.it> X-Spam-Rating: smtp5.aruba.it 1.6.2 0/1000/N Cc: Subject: Howto prelink to boost performance 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, 18 Feb 2007 21:13:00 -0000 In an openbsd ML I have read that it is possible for a desktop instalation to improve the performance by using the prelinking ability of openbsd similar to that of linux. here the key sentence:"........ prelinking... can be enabled using `ldconfig -P /usr/bin /usr/sbin /usr/local/bin /usr/local/sbin /usr/X11R6/bin'. This should result in a noticeable speed increase, especially on programs with lots of loaded libraries ...................." (mozilla, firefox, etc.) In freebsd 6.2 the option -P doesn't seem to exist for ldconfig. How could I - under freebsd - get the same result (prelink I mean!)? Ciao Vittorio From owner-freebsd-performance@FreeBSD.ORG Fri Feb 23 13:27:13 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id CE74416A400 for ; Fri, 23 Feb 2007 13:27:13 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.freebsd.org (Postfix) with ESMTP id 6C3FB13C481 for ; Fri, 23 Feb 2007 13:27:13 +0000 (UTC) (envelope-from killing@multiplay.co.uk) X-Spam-Checker-Version: SpamAssassin 3.1.5 (2006-08-29) on core6.multiplay.co.uk X-Spam-Level: X-Spam-Status: No, score=-24.7 required=6.0 tests=BAYES_00, USER_IN_WHITELIST, USER_IN_WHITELIST_TO autolearn=ham version=3.1.5 Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon PRO v9.5.4) with ESMTP id md50003552633.msg; Fri, 23 Feb 2007 13:11:48 +0000 Message-ID: <0e2001c7574c$26bc15a0$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: , Date: Fri, 23 Feb 2007 13:11:29 -0000 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=original Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.3028 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.3028 X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-Envelope-From: killing@multiplay.co.uk X-Spam-Processed: multiplay.co.uk, Fri, 23 Feb 2007 13:11:48 +0000 X-MDAV-Processed: multiplay.co.uk, Fri, 23 Feb 2007 13:11:49 +0000 Cc: Subject: FreeBSD Scaling on 6.2-RELEASE? 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, 23 Feb 2007 13:27:13 -0000 I'm looking at new machines for high access forums / DB and wonder if anyone has any experience with how well FreeBSD specifically 6.2 scales on Dual Quad Core Intel's. We have some Dual Dual Core's here but I'm considering the Quad Core upgrade but am a little concerned that this may start to become OS limited given the 8 Cores. The software we will be running is vBulletin so apache + php and mysql. Does anyone have any experience / results they can share? Regards Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Fri Feb 23 14:07:22 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id EC55F16A400 for ; Fri, 23 Feb 2007 14:07:22 +0000 (UTC) (envelope-from kometen@gmail.com) Received: from ug-out-1314.google.com (ug-out-1314.google.com [66.249.92.172]) by mx1.freebsd.org (Postfix) with ESMTP id 8450513C481 for ; Fri, 23 Feb 2007 14:07:22 +0000 (UTC) (envelope-from kometen@gmail.com) Received: by ug-out-1314.google.com with SMTP id 71so341017ugh for ; Fri, 23 Feb 2007 06:07:21 -0800 (PST) DKIM-Signature: a=rsa-sha1; c=relaxed/relaxed; d=gmail.com; s=beta; h=domainkey-signature:received:received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=PW9zff9OGFpDHgyyUOlgk/IEn55fzG1k2ynMfahAMwsZVHi5JoNzSY6qzjxu/jkN46oA+oKyf/anfqWzjU+uiFSS5gAGI9z3yvSt5KK8GS3EfhgJc4ZOUsifilsEPPgONNeCq81q9L3gbN4tC8+xThGC8eiBWoyiQrjSpRvPpWg= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=d7t+Ziv35P8TByxErXQmJbzYD8t7mlXaxhSB/CHx8dnel0tW6OG6FLgv0xUT4NqNWrph6eASjhayS4UnZcEwIkDF/rybu7JiaJ8wXukEIBR11335uQFFgNngMCZbT9BDWZntip3Sl26mCtCSDiLafkXzCI9+npl1Ox4dN/iQ+VE= Received: by 10.78.193.5 with SMTP id q5mr165891huf.1172239641232; Fri, 23 Feb 2007 06:07:21 -0800 (PST) Received: by 10.78.100.9 with HTTP; Fri, 23 Feb 2007 06:07:21 -0800 (PST) Message-ID: Date: Fri, 23 Feb 2007 15:07:21 +0100 From: "Claus Guttesen" To: "Steven Hartland" In-Reply-To: <0e2001c7574c$26bc15a0$b3db87d4@multiplay.co.uk> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline References: <0e2001c7574c$26bc15a0$b3db87d4@multiplay.co.uk> Cc: freebsd-hackers@freebsd.org, freebsd-performance@freebsd.org Subject: Re: FreeBSD Scaling on 6.2-RELEASE? 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, 23 Feb 2007 14:07:23 -0000 > I'm looking at new machines for high access forums / DB > and wonder if anyone has any experience with how well > FreeBSD specifically 6.2 scales on Dual Quad Core Intel's. > > We have some Dual Dual Core's here but I'm considering > the Quad Core upgrade but am a little concerned that > this may start to become OS limited given the 8 Cores. > > The software we will be running is vBulletin so apache + > php and mysql. > > Does anyone have any experience / results they can share? Just read http://osnews.com/story.php/17342/Breakthrough-in-MySQL-Performance-on-FreeBSD where FreeBSD shows very promising performance on more than 4 cpu's running mysql. (But) the results are based on current (7.0). This can be proven stable "enough" though if the server can be exposed to real-world traffic. regards Claus From owner-freebsd-performance@FreeBSD.ORG Fri Feb 23 14:54:53 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id C90E916A401 for ; Fri, 23 Feb 2007 14:54:53 +0000 (UTC) (envelope-from ap@bnc.net) Received: from mailomat.net (mailomat.net [217.110.117.101]) by mx1.freebsd.org (Postfix) with ESMTP id 6371313C48D for ; Fri, 23 Feb 2007 14:54:52 +0000 (UTC) (envelope-from ap@bnc.net) X-Spam-Checker-Version: SpamAssassin 3.1.7 (2006-10-05) on f-1.mailomat.net X-Spam-Level: X-Spam-Status: No, hits=-3.9 required=4.0 tests=ALL_TRUSTED=-1.8, AWL=0.500, BAYES_00=-2.599 autolearn=ham version=3.1.7 X-TFF-CGPSA-Version: 1.5 X-Mailomat-CGPSA-Filter: Scanned X-Mailomat-SpamCatcher-Score: 2 [X] X-Mailomat-Cloudmark-Score: 0.000000 [] Received: from [87.234.79.113] (account ap HELO [194.39.192.148]) by mailomat.net (CommuniGate Pro SMTP 5.1.5) with ESMTPSA id 16069171; Fri, 23 Feb 2007 14:54:45 +0100 In-Reply-To: <0e2001c7574c$26bc15a0$b3db87d4@multiplay.co.uk> References: <0e2001c7574c$26bc15a0$b3db87d4@multiplay.co.uk> Mime-Version: 1.0 (Apple Message framework v752.3) X-Priority: 3 Content-Type: text/plain; charset=US-ASCII; format=flowed Message-Id: <8D56B6FB-0874-4836-A3B8-5CA6299BC032@bnc.net> Content-Transfer-Encoding: 7bit From: Achim Patzner Date: Fri, 23 Feb 2007 14:54:34 +0100 To: "Steven Hartland" X-Mailer: Apple Mail (2.752.3) Cc: FreeBSD Performance Subject: Re: FreeBSD Scaling on 6.2-RELEASE? 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, 23 Feb 2007 14:54:53 -0000 On 23.02.2007, at 14:11, Steven Hartland wrote: > We have some Dual Dual Core's here but I'm considering > the Quad Core upgrade but am a little concerned that > this may start to become OS limited given the 8 Cores. Well... It's definitely better on our Xeon 5355 compute servers (Intel SR1500-based) than Xeon 50xx on Hyper Threading. But as the servers are used for jobs requiring rather low IO rates that won't tell you much regarding > running is vBulletin so apache + > php and mysql. except that the machines aren't crashing for having too many CPUs. Achim From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 00:53:34 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 191A516A402 for ; Sat, 24 Feb 2007 00:53:34 +0000 (UTC) (envelope-from lists@stringsutils.com) Received: from zoraida.natserv.net (p65-147.acedsl.com [66.114.65.147]) by mx1.freebsd.org (Postfix) with ESMTP id CA6CD13C442 for ; Sat, 24 Feb 2007 00:53:33 +0000 (UTC) (envelope-from lists@stringsutils.com) Received: from zoraida.natserv.net (localhost.natserv.net [127.0.0.1]) by zoraida.natserv.net (Postfix) with ESMTP id AC1D3C316 for ; Fri, 23 Feb 2007 19:32:32 -0500 (EST) Received: by zoraida.natserv.net (Postfix, from userid 58) id 54B45C2E9; Fri, 23 Feb 2007 19:32:32 -0500 (EST) X-Spam-Flag: YES X-Spam-Checker-Version: SpamAssassin 3.1.7 (2006-10-05) on zoraida.natserv.net X-Spam-Level: **** X-Spam-Status: Yes, score=4.3 required=4.0 tests=RCVD_IN_FIVETENSRC, RCVD_IN_NOMOREFUNN,SPF_FAIL autolearn=disabled version=3.1.7 X-Spam-Report: * 1.3 SPF_FAIL SPF: sender does not match SPF record (fail) * [SPF failed: Please see http://www.openspf.org/why.html?sender=lists%40stringsutils.com&ip=71.249.233.130&receiver=zoraida.natserv.net] * 1.0 RCVD_IN_FIVETENSRC RBL: Received via a relay in Five Ten block list * [71.249.233.130 listed in blackholes.five-ten-sg.com] * 2.0 RCVD_IN_NOMOREFUNN RBL: Received via a relay in No More Funn block * list * [71.249.233.130 listed in no-more-funn.moensted.dk] Received: from 35st.simplicato.com (static-71-249-233-130.nycmny.east.verizon.net [71.249.233.130]) by zoraida.natserv.net (Postfix) with ESMTP id F145DC2AF; Fri, 23 Feb 2007 19:32:29 -0500 (EST) References: <0e2001c7574c$26bc15a0$b3db87d4@multiplay.co.uk> Message-ID: X-Mailer: http://www.courier-mta.org/cone/ From: Francisco Reyes To: Steven Hartland Date: Fri, 23 Feb 2007 19:32:28 -0500 Mime-Version: 1.0 Content-Type: text/plain; format=flowed; charset="US-ASCII" Content-Disposition: inline Content-Transfer-Encoding: 7bit X-Spam-Prev-Subject: Re: FreeBSD Scaling on 6.2-RELEASE? X-Virus-Scanned: ClamAV using ClamSMTP Cc: freebsd-performance@freebsd.org Subject: *****SPAM***** Re: FreeBSD Scaling on 6.2-RELEASE? 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, 24 Feb 2007 00:53:34 -0000 Steven Hartland writes: > The software we will be running is vBulletin so apache + > php and mysql. Mysql is thread based. Quadcore will not help the DB side. Will help with the other components though, if you host everything in the same machine. From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 00:57:50 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9DA6716A407 for ; Sat, 24 Feb 2007 00:57:50 +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 8C0C713C442 for ; Sat, 24 Feb 2007 00:57:50 +0000 (UTC) (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 4464F1A4D9A; Fri, 23 Feb 2007 16:57:50 -0800 (PST) Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id A8CBB515B2; Fri, 23 Feb 2007 19:57:48 -0500 (EST) Date: Fri, 23 Feb 2007 19:57:48 -0500 From: Kris Kennaway To: Francisco Reyes Message-ID: <20070224005748.GA25295@xor.obsecurity.org> References: <0e2001c7574c$26bc15a0$b3db87d4@multiplay.co.uk> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4.2.2i Cc: freebsd-performance@freebsd.org, Steven Hartland Subject: Re: *****SPAM***** Re: FreeBSD Scaling on 6.2-RELEASE? 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, 24 Feb 2007 00:57:50 -0000 On Fri, Feb 23, 2007 at 07:32:28PM -0500, Francisco Reyes wrote: > Steven Hartland writes: > > >The software we will be running is vBulletin so apache + > >php and mysql. > > Mysql is thread based. Quadcore will not help the DB side. Will help with > the other components though, if you host everything in the same machine. ? Actually it will help the DB side, when you have multiple simultaneous transactions - that's the point :) Kris From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 12:15:58 2007 Return-Path: X-Original-To: performance@FreeBSD.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 84C7116A401 for ; Sat, 24 Feb 2007 12:15:58 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.freebsd.org (Postfix) with ESMTP id 5D48B13C428 for ; Sat, 24 Feb 2007 12:15:58 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id 4935446FBA; Sat, 24 Feb 2007 06:47:34 -0500 (EST) Date: Sat, 24 Feb 2007 11:47:34 +0000 (GMT) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: current@FreeBSD.org Message-ID: <20070224095324.K36322@fledge.watson.org> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: performance@FreeBSD.org Subject: Fine-grained locking for UNIX domain sockets: patch updated 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, 24 Feb 2007 12:15:58 -0000 As part of Kris and Jeff's recent work on improving MySQL scalability on FreeBSD, I've updated my fine-grained locking patch for UNIX domain sockets to a more recent 7-CURRENT: http://www.watson.org/~robert/freebsd/netperf/20070224-uds-fine-grain.diff This patch replaces the global mutex with a global rwlock, and introduces per-unpcb locks to protect the state of each socket at the UNIX domain socket layer. Depending on the protocol operation, either the per-unpcb mutex is sufficient, or global read or write locks may also be required. The role of the global lock is to protect the topology of the connections between sockets, protect vnode v_socket pointers, and to prevent lock order issues in the event the per-unpcb lock of more than one socket must be acquired at a time. For example, exclusive global locking is required during bind() and connect() to protect v_socket and change the topology of connected sockets, whereas recv() requires only the unpcb lock of the receiving socket. send() may require either just an unpcb lock or a global lock if send() is implicitly connecting (sendto()) or disconnecting (PRUS_EOF) a socket. This is basically the same patch that I have been maintaining since 2005 and posted at intermittent intervals when there have been reports of negative performance due to high contention on the UNIX domain socket subsystem lock. I continue to look for performance feedback, especially from workloads that are heavy consumers of UNIX domain sockets (such as MySQL). My experience has been that it gives a small performance hit on workloads and in configurations without much contention/scalability, but a measurable performance benefit with anything more substantial. Decrease in lower end workloads and configurations is at least in part due to the overhead of some additional locking vs. the benefits of reduced contention. Something that I am particularly interested in looking for is little or no performance hit on UP. This is a fairly heavily tested and refined patch, so the issue in deciding whether or not to commit this is its real-world effect on performance. Robert N M Watson Computer Laboratory University of Cambridge From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 12:41:59 2007 Return-Path: X-Original-To: performance@FreeBSD.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 1C73416A401; Sat, 24 Feb 2007 12:41:59 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.freebsd.org (Postfix) with ESMTP id 5FA0D13C494; Sat, 24 Feb 2007 12:41:58 +0000 (UTC) (envelope-from killing@multiplay.co.uk) X-Spam-Checker-Version: SpamAssassin 3.1.5 (2006-08-29) on core6.multiplay.co.uk X-Spam-Level: X-Spam-Status: No, score=-24.7 required=6.0 tests=BAYES_00, USER_IN_WHITELIST, USER_IN_WHITELIST_TO autolearn=ham version=3.1.5 Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon PRO v9.5.4) with ESMTP id md50003556372.msg; Sat, 24 Feb 2007 12:24:29 +0000 Message-ID: <00bc01c7580e$b31e6ad0$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Robert Watson" , References: <20070224095324.K36322@fledge.watson.org> Date: Sat, 24 Feb 2007 12:24:05 -0000 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.3028 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.3028 X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-Envelope-From: killing@multiplay.co.uk X-Spam-Processed: multiplay.co.uk, Sat, 24 Feb 2007 12:24:30 +0000 X-MDAV-Processed: multiplay.co.uk, Sat, 24 Feb 2007 12:24:30 +0000 Cc: performance@FreeBSD.org Subject: Re: Fine-grained locking for UNIX domain sockets: patch updated 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, 24 Feb 2007 12:41:59 -0000 ----- Original Message ----- From: "Robert Watson" > As part of Kris and Jeff's recent work on improving MySQL scalability on > FreeBSD Are there any results / info on what's been done that we can look at? Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 13:53:24 2007 Return-Path: X-Original-To: performance@FreeBSD.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id AB12E16A401; Sat, 24 Feb 2007 13:53:24 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [209.31.154.42]) by mx1.freebsd.org (Postfix) with ESMTP id 8234613C4BB; Sat, 24 Feb 2007 13:53:24 +0000 (UTC) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [209.31.154.41]) by cyrus.watson.org (Postfix) with ESMTP id 11C764991E; Sat, 24 Feb 2007 08:53:24 -0500 (EST) Date: Sat, 24 Feb 2007 13:53:23 +0000 (GMT) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: Steven Hartland In-Reply-To: <00bc01c7580e$b31e6ad0$b3db87d4@multiplay.co.uk> Message-ID: <20070224135154.H36322@fledge.watson.org> References: <20070224095324.K36322@fledge.watson.org> <00bc01c7580e$b31e6ad0$b3db87d4@multiplay.co.uk> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: performance@FreeBSD.org, current@FreeBSD.org Subject: Re: Fine-grained locking for UNIX domain sockets: patch updated 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, 24 Feb 2007 13:53:24 -0000 On Sat, 24 Feb 2007, Steven Hartland wrote: > ----- Original Message ----- From: "Robert Watson" >> As part of Kris and Jeff's recent work on improving MySQL scalability on >> FreeBSD > > Are there any results / info on what's been done that we can look at? I understand that Kris is preparing a summary to post to the lists in the next couple of days. The thrust of the work has been an investigation of MySQL on an 8-core system, and in particular, how to improve FreeBSD scalability with an increase in concurrency. The preliminary results have been quite impressive and show extremely competitive performance when compared with another mainstream open source OS. But I won't steal their thunder, and instead encourage you to look out for the posting. :-) Robert N M Watson Computer Laboratory University of Cambridge From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 13:15:17 2007 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id F395316A400 for ; Sat, 24 Feb 2007 13:15:16 +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 82F8113C461 for ; Sat, 24 Feb 2007 13:15:16 +0000 (UTC) (envelope-from gofp-freebsd-performance@m.gmane.org) Received: from root by ciao.gmane.org with local (Exim 4.43) id 1HKwju-0000ew-IM for freebsd-performance@freebsd.org; Sat, 24 Feb 2007 14:15:03 +0100 Received: from r4v24.net.upc.cz ([84.42.149.24]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Sat, 24 Feb 2007 14:15:02 +0100 Received: from v.haisman by r4v24.net.upc.cz with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Sat, 24 Feb 2007 14:15:02 +0100 X-Injected-Via-Gmane: http://gmane.org/ To: freebsd-performance@freebsd.org From: =?UTF-8?B?VsOhY2xhdiBIYWlzbWFu?= Date: Sat, 24 Feb 2007 14:12:01 +0100 Lines: 45 Message-ID: <45E039A1.6030100@sh.cvut.cz> References: Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig7D1CCFF6EF24D5C51B1AC7B5" X-Complaints-To: usenet@sea.gmane.org Cc: freebsd-performance@freebsd.org X-Gmane-NNTP-Posting-Host: r4v24.net.upc.cz User-Agent: Thunderbird 1.5.0.9 (Windows/20061207) In-Reply-To: X-Enigmail-Version: 0.94.2.0 OpenPGP: id=63B6B297 Sender: news X-Mailman-Approved-At: Sat, 24 Feb 2007 14:10:18 +0000 Subject: Re: Virtual performance 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, 24 Feb 2007 13:15:17 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig7D1CCFF6EF24D5C51B1AC7B5 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Ivan Voras wrote, On 17.2.2007 13:46: > Vlad GALU wrote: >=20 >> At work, we have several build guests running FreeBSD. Overall it >> seems to be a timer problem when running in VMware. Running >> vmware-guestd helped in almost all circumstances. The worst cases we >> saw were in processes who were sleep()-ing. >=20 > My frst thought was that something's wrong with timers, but it's slow i= n > "real" time (walltime). >=20 I have similar problems with FreeBSD under MS Virtual Server 2005 R2. I regained most of the speed/accuracy of clock setting kern.hz=3D2000 in /boot/loader.conf. -- Vaclav Haisman --------------enig7D1CCFF6EF24D5C51B1AC7B5 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (MingW32) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org iQEVAwUBReA5qENOZDESBK8FAQKzUwf/aPCYuVB+wsxy4BQVVIh2HVJPZaKqSMr4 xF3Wg1K99psGb39K2UASKUIiTBdtdtei8hJbo3P06i38cAfuKCxH8p8LjmzNLFFi GybKycNdlaYL/k5NKsR0D+HzaKR0WD80eXyuoguFJcTILDCvgoxfPg8/xNJU0Tjx oQHAkECeTaVDhP4+8ioVSKjaCx73W65UaJRKKIPHV3UaxyL1fgd2DJvQjdFhIiES O41GTBV+zB3LgGHzruO8nhUnhlSWdGRLgSH2jzxCr0Q0BsIvEP03XMZRB/K+RKr9 RQ2rO4YyuZ/pVsmCszBMiatb4i21gx8srJ0lPmwsZ7b0bhECVyLfHw== =zqEF -----END PGP SIGNATURE----- --------------enig7D1CCFF6EF24D5C51B1AC7B5-- From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 13:47:09 2007 Return-Path: X-Original-To: performance@freebsd.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id A93DC16A402; Sat, 24 Feb 2007 13:47:09 +0000 (UTC) (envelope-from jhary@unsane.co.uk) Received: from unsane.co.uk (www.unsane.co.uk [85.233.185.162]) by mx1.freebsd.org (Postfix) with ESMTP id 3B8E713C461; Sat, 24 Feb 2007 13:47:09 +0000 (UTC) (envelope-from jhary@unsane.co.uk) Received: from [192.168.10.217] ([192.168.10.217]) (authenticated bits=0) by unsane.co.uk (8.14.0/8.13.8) with ESMTP id l1ODWPOR011346 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Sat, 24 Feb 2007 13:32:26 GMT (envelope-from jhary@unsane.co.uk) Message-ID: <45E03E5B.7010104@unsane.co.uk> Date: Sat, 24 Feb 2007 13:32:11 +0000 From: Vince User-Agent: Thunderbird 1.5.0.9 (X11/20070129) MIME-Version: 1.0 References: <20070224095324.K36322@fledge.watson.org> <00bc01c7580e$b31e6ad0$b3db87d4@multiplay.co.uk> In-Reply-To: <00bc01c7580e$b31e6ad0$b3db87d4@multiplay.co.uk> X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sat, 24 Feb 2007 14:10:29 +0000 Cc: performance@freebsd.org, current@freebsd.org Subject: Re: Fine-grained locking for UNIX domain sockets: patch updated 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, 24 Feb 2007 13:47:09 -0000 Steven Hartland wrote: > ----- Original Message ----- From: "Robert Watson" >> As part of Kris and Jeff's recent work on improving MySQL scalability >> on FreeBSD > > Are there any results / info on what's been done that we can look at? > > Steve > Jeff's Blog would be the place for these. http://jeffr-tech.livejournal.com Vince > > ================================================ > This e.mail is private and confidential between Multiplay (UK) Ltd. and > the person or entity to whom it is addressed. In the event of > misdirection, the recipient is prohibited from using, copying, printing > or otherwise disseminating it or any information contained in it. > In the event of misdirection, illegible or incomplete transmission > please telephone +44 845 868 1337 > or return the E.mail to postmaster@multiplay.co.uk. > > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 18:22:03 2007 Return-Path: X-Original-To: performance@FreeBSD.org Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 99E4616A405; Sat, 24 Feb 2007 18:22:03 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.freebsd.org (Postfix) with ESMTP id DCB6713C478; Sat, 24 Feb 2007 18:22:02 +0000 (UTC) (envelope-from killing@multiplay.co.uk) X-Spam-Checker-Version: SpamAssassin 3.1.5 (2006-08-29) on core6.multiplay.co.uk X-Spam-Level: X-Spam-Status: No, score=-24.7 required=6.0 tests=BAYES_00, USER_IN_WHITELIST, USER_IN_WHITELIST_TO autolearn=ham version=3.1.5 Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon PRO v9.5.4) with ESMTP id md50003557582.msg; Sat, 24 Feb 2007 18:17:41 +0000 Message-ID: <011501c75840$0c14a7e0$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Robert Watson" References: <20070224095324.K36322@fledge.watson.org> <00bc01c7580e$b31e6ad0$b3db87d4@multiplay.co.uk> <20070224135154.H36322@fledge.watson.org> Date: Sat, 24 Feb 2007 18:17:22 -0000 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.3028 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.3028 X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-Envelope-From: killing@multiplay.co.uk X-Spam-Processed: multiplay.co.uk, Sat, 24 Feb 2007 18:17:41 +0000 X-MDAV-Processed: multiplay.co.uk, Sat, 24 Feb 2007 18:17:41 +0000 Cc: performance@FreeBSD.org, current@FreeBSD.org Subject: Re: Fine-grained locking for UNIX domain sockets: patch updated 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, 24 Feb 2007 18:22:03 -0000 ----- Original Message ----- From: "Robert Watson" > I understand that Kris is preparing a summary to post to the lists in the next > couple of days. The thrust of the work has been an investigation of MySQL on > an 8-core system, and in particular, how to improve FreeBSD scalability with > an increase in concurrency. The preliminary results have been quite > impressive and show extremely competitive performance when compared with > another mainstream open source OS. But I won't steal their thunder, and > instead encourage you to look out for the posting. :-) Exciting stuff look forward to seeing this as that's just what we are looking to put into production an 8 way mysql server. Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Sat Feb 24 21:55:11 2007 Return-Path: X-Original-To: freebsd-performance@FreeBSD.org Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 297E616A401 for ; Sat, 24 Feb 2007 21:55:11 +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 1AE9E13C481 for ; Sat, 24 Feb 2007 21:55:11 +0000 (UTC) (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 7F7A21A4D80 for ; Sat, 24 Feb 2007 13:55:09 -0800 (PST) Received: by obsecurity.dyndns.org (Postfix, from userid 1000) id BE6B7517C9; Sat, 24 Feb 2007 16:55:08 -0500 (EST) Date: Sat, 24 Feb 2007 16:55:08 -0500 From: Kris Kennaway To: freebsd-performance@FreeBSD.org Message-ID: <20070224215508.GA41968@xor.obsecurity.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.2.2i Cc: Subject: Progress on scaling of FreeBSD on 8 CPU systems 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, 24 Feb 2007 21:55:11 -0000 Now that the goals of the SMPng project are complete, for the past year or more several of us have been working hard on profiling FreeBSD in various multiprocessor workloads, and looking for performance bottlenecks to be optimized. We have recently made significant progress on optimizing for MySQL running on an 8-core amd64 system. The graph of results may be found here: http://www.freebsd.org/~kris/scaling/scaling.png This shows the graph of MySQL transactions/second performed by a multi-threaded client workload against a local MySQL database with varying numbers of client threads, with identically configured FreeBSD and Linux systems on the same machine. The test was run on FreeBSD 7.0, with the latest version of the ULE 2.0 scheduler, the libthr threading library, and an uncommitted patch from Jeff Roberson [1] that addresses poor scalability of file descriptor locking (using a new sleepable mutex primitive); this patch is responsible for almost all of the performance and scaling improvements measured. It also includes some other patches (collected in my kris-contention p4 branch) that have been shown to help contention in MySQL workloads in the past (including a UNIX domain socket locking pushdown patch from Robert Watson), but these were shown to only give small individual contributions, with a cumulative effect on the order of 5-10%. With this configuration we are able to achieve performance that is consistent with Linux at peak (the graph shows Linux 2% faster, but this is commensurate with the margin of error coming from variance between runs, so more data is needed to distinguish them), with 8 client threads (=1 thread/CPU core), and significantly outperforms Linux at higher than peak loads, when running on the same hardware. Specifically, beyond 8 client threads FreeBSD has only minor performance degradation (an 8% drop from peak throughput at 8 clients to 20 clients), but Linux collapses immediately above 8 threads, and above 14 threads asymptotes to essentially single-threaded levels. At 20 clients FreeBSD outperforms Linux by a factor of 4. We see this result as part of the payoff we are seeing from the hard work of many developers over the past 7 years. In particular it is a significant validation of the SMP and locking strategies chosen for the FreeBSD kernel in the post-FreeBSD 4.x world. More configuration details and discussion about the benchmark may be found here: http://people.freebsd.org/~kris/scaling/mysql.html Kris