From owner-freebsd-performance@FreeBSD.ORG Mon Oct 20 03:06:50 2003 Return-Path: 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 7A2CD16A4BF for ; Mon, 20 Oct 2003 03:06:50 -0700 (PDT) Received: from web40602.mail.yahoo.com (web40602.mail.yahoo.com [66.218.78.139]) by mx1.FreeBSD.org (Postfix) with SMTP id 994DC43F75 for ; Mon, 20 Oct 2003 03:06:49 -0700 (PDT) (envelope-from pjn0211@yahoo.com) Message-ID: <20031020100649.25805.qmail@web40602.mail.yahoo.com> Received: from [203.146.50.38] by web40602.mail.yahoo.com via HTTP; Mon, 20 Oct 2003 11:06:49 BST Date: Mon, 20 Oct 2003 11:06:49 +0100 (BST) From: =?iso-8859-1?q?Supote=20Leelasupphakorn?= To: freebsd-performance@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Mailman-Approved-At: Mon, 20 Oct 2003 13:56:20 -0700 cc: freebsd-questions@freebsd.org Subject: Have anyone seen this benchmark ? X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 20 Oct 2003 10:06:50 -0000 Hi, all I saw this on www.OsNews.com (http://bulk.fefe.de/scalability/) but no FreeBSD_4. Is there any benchmark between linux-2.6 and FreeBSD_4 in various aspects. Or any comments are welcome, pjn ________________________________________________________________________ Want to chat instantly with your online friends? Get the FREE Yahoo! Messenger http://mail.messenger.yahoo.co.uk From owner-freebsd-performance@FreeBSD.ORG Fri Oct 24 07:22:41 2003 Return-Path: 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 636F216A4B3 for ; Fri, 24 Oct 2003 07:22:41 -0700 (PDT) Received: from codeblau.de (codeblau.walledcity.de [212.84.209.34]) by mx1.FreeBSD.org (Postfix) with ESMTP id C228F43FE3 for ; Fri, 24 Oct 2003 07:22:37 -0700 (PDT) (envelope-from felix-benchmark@fefe.de) Received: (qmail 10002 invoked by uid 100); 24 Oct 2003 14:23:45 -0000 Date: Fri, 24 Oct 2003 16:23:45 +0200 From: Felix von Leitner To: freebsd-performance@freebsd.org Message-ID: <20031024142345.GA9997@codeblau.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.5.4i X-Mailman-Approved-At: Fri, 24 Oct 2003 15:10:58 -0700 Subject: Please help me tune FreeBSD for bulk.fefe.de/scalability/ X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 24 Oct 2003 14:22:41 -0000 Hi! Several people have asked me to re-run my benchmarks after the kernels have been properly tuned. To ensure a fair test, I will ask each kernel team to send me a list of things to do to a GENERIC kernel to optimize it for optimal performance on my benchmarks. Please also tell me if you have suggestions for other benchmarks that say something about the scalability of an operating system, that I could (and should) include in my benchmark suite. Felix From owner-freebsd-performance@FreeBSD.ORG Fri Oct 24 15:27:46 2003 Return-Path: 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 9C07C16A4BF for ; Fri, 24 Oct 2003 15:27:46 -0700 (PDT) Received: from perrin.nxad.com (internal.nxad.com [69.1.70.251]) by mx1.FreeBSD.org (Postfix) with ESMTP id F05B343FDD for ; Fri, 24 Oct 2003 15:27:43 -0700 (PDT) (envelope-from sean@nxad.com) Received: by perrin.nxad.com (Postfix, from userid 1001) id 5F7EF21065; Fri, 24 Oct 2003 15:27:43 -0700 (PDT) Date: Fri, 24 Oct 2003 15:27:43 -0700 From: Sean Chittenden To: Felix von Leitner Message-ID: <20031024222743.GC13386@perrin.nxad.com> References: <20031024142345.GA9997@codeblau.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20031024142345.GA9997@codeblau.de> X-PGP-Key: finger seanc@FreeBSD.org X-PGP-Fingerprint: 3849 3760 1AFE 7B17 11A0 83A6 DD99 E31F BC84 B341 X-Web-Homepage: http://sean.chittenden.org/ User-Agent: Mutt/1.5.4i cc: freebsd-performance@freebsd.org Subject: Re: Please help me tune FreeBSD for bulk.fefe.de/scalability/ X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 24 Oct 2003 22:27:46 -0000 > Please also tell me if you have suggestions for other benchmarks > that say something about the scalability of an operating system, > that I could (and should) include in my benchmark suite. >From a database perspective, I have two benchmarks that I'd be interested in seeing. 1) Time required to read a frequently accessed page that has been mmap()'ed. As you state, it takes FreeBSD longer to mmap() the first page, but I'd like to see the benefit for the startup time documented in a benchmark. Presumably, the extra time required to load the first page is worth something. 2) Time required to read a frequently accessed page that has not been mmap()'ed (ie, raw read() IO). I'd like to know how fast each OS's file system cache is. A few other comments about your benchmarking (which are really great to have, thank you!): 1) Are you using the most recent version of FreeBSD-CURRENT? If so, I'd be curious to have libpthreads/libkse benchmarked. Time to spawn a new thread and time required to join ten threads. Something like that would be quasi-useful. 2) You state in your mmap benchmark section: "As you can see, Linux 2.4 appears to scale O(n), while Linux 2.6 is O(1). FreeBSD looks to be much faster than Linux 2.6, but you need to keep in mind that FreeBSD took an extraordinary time to do the actual mmap, so this good result does not save the day for FreeBSD." I would disagree in that it is the common case for an mmap()'ed page to be simultaneously mmap()'ed by other processes (think Apache serving a busy homepage: each proc is mmap()'ing the same file). I'd imagine that FreeBSD would win in a performance test of this nature because of the work it did when it mmap()'ed the first page, therefore think that this proves that FreeBSD is justified in the extra time that it takes when mmap()'ing a new page. 3) FreeBSD isn't finished in terms of its locking. That said, these benchmarks really impress me that even though many subsystems are still under the Giant lock, FreeBSD 5.X performs as well, if not better than Linux 2.6. -sc -- Sean Chittenden From owner-freebsd-performance@FreeBSD.ORG Fri Oct 24 16:01:17 2003 Return-Path: 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 8AF5A16A4B3 for ; Fri, 24 Oct 2003 16:01:17 -0700 (PDT) Received: from amsfep13-int.chello.nl (amsfep13-int.chello.nl [213.46.243.24]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1E12D43FBF for ; Fri, 24 Oct 2003 16:01:16 -0700 (PDT) (envelope-from dodell@sitetronics.com) Received: from sitetronics.com ([213.46.142.207]) by amsfep13-int.chello.nl (InterMail vM.5.01.05.17 201-253-122-126-117-20021021) with ESMTP id <20031024230114.YVIA4557.amsfep13-int.chello.nl@sitetronics.com>; Sat, 25 Oct 2003 01:01:14 +0200 Message-ID: <3F99AF34.2050805@sitetronics.com> Date: Sat, 25 Oct 2003 01:01:08 +0200 From: "Devon H. O'Dell" User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.4) Gecko/20030820 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Felix von Leitner , freebsd-performance@freebsd.org References: <20031024142345.GA9997@codeblau.de> In-Reply-To: <20031024142345.GA9997@codeblau.de> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: Please help me tune FreeBSD for bulk.fefe.de/scalability/ X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 24 Oct 2003 23:01:17 -0000 Felix von Leitner wrote: >Hi! > >Several people have asked me to re-run my benchmarks after the kernels >have been properly tuned. > Hey Felix, To be totally fair, I'd like to point out the messages from freebsd-hackers that were sent earlier today: On Fri, 24 Oct 2003, Michel TALON wrote: >> What is more interesting is to look at the actual benchmark results in >> http://bulk.fefe.de/scalability/ >> in particular the section about mmap benchmarks, the only one where >> OpenBSD shines. However as soon as touching pages is benchmarked >> OpenBSD fails very much. > > look closer. openbsd's "touch page" times are identical to what you'd expect a disk access to be. the pages aren't cached, they're read from disk. so compared to systems that don't read from disk, it looks pretty bad. a 5 line patch to fix the benchmark so that the file actually is cached on openbsd results in performance much in line with freebsd/linux. The above is a reply by Ted Unangst; perhaps you'd like to look into this. --Devon From owner-freebsd-performance@FreeBSD.ORG Fri Oct 24 16:24:29 2003 Return-Path: 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 E528716A4B3 for ; Fri, 24 Oct 2003 16:24:29 -0700 (PDT) Received: from mailbox.univie.ac.at (mail.univie.ac.at [131.130.1.27]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8361143FE0 for ; Fri, 24 Oct 2003 16:24:28 -0700 (PDT) (envelope-from l.ertl@univie.ac.at) Received: from dialin202.cc.univie.ac.at (dialin202.cc.univie.ac.at [131.130.202.202])h9ONNuSR421236; Sat, 25 Oct 2003 01:24:03 +0200 Date: Sat, 25 Oct 2003 01:23:48 +0200 (CEST) From: Lukas Ertl To: Felix von Leitner In-Reply-To: <20031024142345.GA9997@codeblau.de> Message-ID: <20031025010928.V846@korben.in.tern> References: <20031024142345.GA9997@codeblau.de> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-DCC-ZID-Univie-Metrics: imap 4243; Body=0 Fuz1=0 Fuz2=0 cc: freebsd-performance@freebsd.org Subject: Re: Please help me tune FreeBSD for bulk.fefe.de/scalability/ X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 24 Oct 2003 23:24:30 -0000 On Fri, 24 Oct 2003, Felix von Leitner wrote: > Please also tell me if you have suggestions for other benchmarks that > say something about the scalability of an operating system, that I could > (and should) include in my benchmark suite. If you have some spare time, I'd really be interested in how the new SCHED_ULE scheduler compares against the traditional (default) SCHED_4BSD scheduler (although SCHED_ULE has been designed for SMP, some UP results are sure nice to have). Regarding performance tuning: did you already look at accf_http(9) and/or accf_data(9)? (Although it would probably need some rewrite of your code...) regards, le -- Lukas Ertl eMail: l.ertl@univie.ac.at UNIX Systemadministrator Tel.: (+43 1) 4277-14073 Vienna University Computer Center Fax.: (+43 1) 4277-9140 University of Vienna http://mailbox.univie.ac.at/~le/ From owner-freebsd-performance@FreeBSD.ORG Fri Oct 24 17:15:54 2003 Return-Path: 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 B62A116A4B3 for ; Fri, 24 Oct 2003 17:15:54 -0700 (PDT) Received: from mail.chesapeake.net (chesapeake.net [208.142.252.6]) by mx1.FreeBSD.org (Postfix) with ESMTP id 92EA643FD7 for ; Fri, 24 Oct 2003 17:15:53 -0700 (PDT) (envelope-from jroberson@chesapeake.net) Received: from localhost (jroberson@localhost) by mail.chesapeake.net (8.11.6/8.11.6) with ESMTP id h9P0Dmp64687; Fri, 24 Oct 2003 20:13:48 -0400 (EDT) (envelope-from jroberson@chesapeake.net) Date: Fri, 24 Oct 2003 20:13:48 -0400 (EDT) From: Jeff Roberson To: Lukas Ertl In-Reply-To: <20031025010928.V846@korben.in.tern> Message-ID: <20031024201256.G43805-100000@mail.chesapeake.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII cc: Felix von Leitner cc: freebsd-performance@freebsd.org Subject: Re: Please help me tune FreeBSD for bulk.fefe.de/scalability/ X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 25 Oct 2003 00:15:54 -0000 On Sat, 25 Oct 2003, Lukas Ertl wrote: > On Fri, 24 Oct 2003, Felix von Leitner wrote: > > > Please also tell me if you have suggestions for other benchmarks that > > say something about the scalability of an operating system, that I could > > (and should) include in my benchmark suite. > > If you have some spare time, I'd really be interested in how the new > SCHED_ULE scheduler compares against the traditional (default) SCHED_4BSD > scheduler (although SCHED_ULE has been designed for SMP, some UP results > are sure nice to have). ULE has developed some performance problems. I'm not sure where they came from but I will be working on it in the next few weeks. Until then I wouldn't recommend any benchmarking with it unless the CPU affinity will really be a huge win. > > Regarding performance tuning: did you already look at accf_http(9) and/or > accf_data(9)? (Although it would probably need some rewrite of your > code...) > > regards, > le > > -- > Lukas Ertl eMail: l.ertl@univie.ac.at > UNIX Systemadministrator Tel.: (+43 1) 4277-14073 > Vienna University Computer Center Fax.: (+43 1) 4277-9140 > University of Vienna http://mailbox.univie.ac.at/~le/ > _______________________________________________ > 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 Fri Oct 24 20:25:54 2003 Return-Path: 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 944DA16A4B3 for ; Fri, 24 Oct 2003 20:25:54 -0700 (PDT) Received: from kartoffel.salatschuessel.net (pD9E21148.dip.t-dialin.net [217.226.17.72]) by mx1.FreeBSD.org (Postfix) with ESMTP id A92AD43FB1 for ; Fri, 24 Oct 2003 20:25:50 -0700 (PDT) (envelope-from lehmann@ans-netz.de) Received: from kartoffel.salatschuessel.net (localhost [127.0.0.1]) h9P3PcMH090103 for ; Sat, 25 Oct 2003 05:25:39 +0200 (CEST) (envelope-from lehmann@ans-netz.de) Date: Sat, 25 Oct 2003 05:25:38 +0200 From: Oliver Lehmann To: freebsd-performance@freebsd.org Message-Id: <20031025052538.45afd00b.lehmann@ans-netz.de> In-Reply-To: <20031024142345.GA9997@codeblau.de> References: <20031024142345.GA9997@codeblau.de> X-Mailer: Sylpheed version 0.9.7 (GTK+ 1.2.10; i386-portbld-freebsd4.8) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Re: Please help me tune FreeBSD for bulk.fefe.de/scalability/ X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 25 Oct 2003 03:25:54 -0000 Hi Felix, to increment the sysctl value of kern.maxproc you may want to set it in /boot/loader.conf(5) to get these parameter passed through the kernel. Greetings, Oliver -- Oliver Lehmann @home: lehmann@ans-netz.de @office: oliver.lehmann@mgi.de @www: http://www.pofo.de/ | http://wishlist.ans-netz.de/