From owner-freebsd-performance@FreeBSD.ORG Sun Jun 19 15:56:52 2005 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 7BDDE16A41C; Sun, 19 Jun 2005 15:56:52 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [204.156.12.53]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2B7AB43D1F; Sun, 19 Jun 2005 15:56:52 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [204.156.12.50]) by cyrus.watson.org (Postfix) with ESMTP id 915D246B20; Sun, 19 Jun 2005 11:56:51 -0400 (EDT) Date: Sun, 19 Jun 2005 16:59:30 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: David Sze In-Reply-To: <6.2.1.2.2.20050617091736.05949298@mail.distrust.net> Message-ID: <20050619165349.U6413@fledge.watson.org> References: <746fd037f6ca8131a8fb8938f1e346e9@lonres.com> <20050610170537.GA67849@bibipentium.lonres.com> <20050611085604.J75625@fledge.watson.org> <20050616161506.GB28794@bibipentium.lonres.com> <6.2.1.2.2.20050617091736.05949298@mail.distrust.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed X-Mailman-Approved-At: Mon, 20 Jun 2005 12:01:12 +0000 Cc: Steve Roome , freebsd-stable@freebsd.org, steve@pepcross.com, Jon Dama , Guy Helmer , Kris Kennaway , Greg 'groggy' Lehey , performance@FreeBSD.org, Daniel Eischen , Xin LI , Thomas Hurst Subject: Re: FreeBSD MySQL still WAY slower than Linux 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, 19 Jun 2005 15:56:52 -0000 On Fri, 17 Jun 2005, David Sze wrote: > FreeBSD/amd64 5.4-RELEASE (libpthread, system and process scope) > FreeBSD/amd64 6.0-CURRENT (libpthread, libthr, system and process > scope) > CentOS/amd64 4.0 (i.e. RHEL4.0) > > I couldn't get libthr to work on FreeBSD/amd64 5.4-RELEASE, mysqld would > immediately coredump and the stacktrace looked like it was corrupted > (i.e. hundreds of stack frames, all of which were ???). The libthr in 5.x is basically an early prototype compared to the more mature work on 6.x, so this result is not all that surprising. David Xu has put a very large amount of work into the libthr on 6.x with some very good results. > It turns out that the problem was the same thing everyone usually points > the finger at, but no one actually mentioned this time: Linux mounts > its partitions async by default. I don't have the exact numbers in > front of me right now, but these were the ballpark figures (I'm not > going to separate out results for all of the different threading > libraries for FreeBSD because the deltas weren't huge): This is actually an interesting observation -- on 6.x using P4 Xeon hardware, I've seen a substantial performance improvement from running with libthr with MySQL. Sometimes as much as 30% - 50%. However, amd64 is quite a different beast. BTW, could you run 'file' on the Linux and FreeBSD MySQL binaries and confirm that they're both either 32-bit i386 binaries, or 64-bit amd64 binaries? > That last CentOS number is not a typo, it was an order of magnitude > slower. I didn't try other file systems on CentOS, just the default > ext3. It's possible that reiserfs or xfs might not be as affected by > switching from async to sync. > > So my production server is now happily running mysql 4.1 on 6.0-CURRENT > :). I was interested to observe, in some benchmarking a few months ago, that 4.0 MySQL performance on FreeBSD 6.x is a *lot* faster than 4.1 MySQL performance. I don't track MySQL feature development, but I couldn't help but wonder if either there had been substantial reliability changes that impacted file system semantics (which might be indicated by sync/async issues), or whether there had been a lot of performance optimization work for Linux that had swung its use of IPC/etc primitives towards ones that work better on Linux than FreeBSD? BTW, could you confirm that on 6.x, you're setting /etc/malloc.conf so that it's not scrubbing memory on free()? In particular: ln -s jz /etc/malloc.conf as root. Most 6.x debugging features are set as part of the kernel configuration, and your performance results suggest that you've caught them all already, I think, but this one is user space. Also, make sure you are compiling without INVARIANT_SUPPORT -- for packet send tests, I find that even without INVARIANTS, I see a 4% hit for having INVARIANT_SUPPORT in the kernel. Robert N M Watson From owner-freebsd-performance@FreeBSD.ORG Mon Jun 20 12:49:17 2005 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 3DF2F16A41C for ; Mon, 20 Jun 2005 12:49:17 +0000 (GMT) (envelope-from bde@zeta.org.au) Received: from mailout1.pacific.net.au (mailout1.pacific.net.au [61.8.0.84]) by mx1.FreeBSD.org (Postfix) with ESMTP id CB53443D53 for ; Mon, 20 Jun 2005 12:49:16 +0000 (GMT) (envelope-from bde@zeta.org.au) Received: from mailproxy2.pacific.net.au (mailproxy2.pacific.net.au [61.8.0.87]) by mailout1.pacific.net.au (8.13.4/8.13.4/Debian-1) with ESMTP id j5KCn3pf001903; Mon, 20 Jun 2005 22:49:03 +1000 Received: from katana.zip.com.au (katana.zip.com.au [61.8.7.246]) by mailproxy2.pacific.net.au (8.13.4/8.13.4/Debian-3) with ESMTP id j5KCn1l4017502; Mon, 20 Jun 2005 22:49:02 +1000 Date: Mon, 20 Jun 2005 22:49:00 +1000 (EST) From: Bruce Evans X-X-Sender: bde@delplex.bde.org To: scuba@centroin.com.br In-Reply-To: Message-ID: <20050620222051.T13863@delplex.bde.org> References: MIME-Version: 1.0 Content-Type: MULTIPART/MIXED; BOUNDARY="0-362250242-1119271740=:13863" Cc: freebsd-performance@FreeBSD.org Subject: Re: Slave IDE HDD not working in UDMA5 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, 20 Jun 2005 12:49:17 -0000 This message is in MIME format. The first part should be readable text, while the remaining parts are likely unreadable without MIME-aware tools. --0-362250242-1119271740=:13863 Content-Type: TEXT/PLAIN; charset=X-UNKNOWN; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE On Thu, 16 Jun 2005 scuba@centroin.com.br wrote: > =09This was first posted on freebsd-question, but I could not find > the solution yet. > =09Maybe you could help me. Maybe a little. I don't use 5.4... > =09I=B4ve installed FreeBSD 5.4 on a new machine with the following > hardware: > > =09Asus P4P800 SE (BIOS v. 1008) > =092GB RAM ( 4x 512 DDR400 ) > =092 HDD Samsung SP0802N (80GB 7200rpm ata-100) 80 pins cable. > > =09The HD were formated with newfs defaults, and the following > results were the same using both as master (primary e secondary) or with = a > master / slave (same interface). > > =09With diskinfo both performance are the same, but with "dd", the > second disc (the slave or the secondary master), is always worst as if it > were working in DMA2. I remember a commit to the ata driver to fix misprogramming of DMA timing= =20 on an Intel chipset for devices and/or channels other than the first. I'm not sure if 5.4 has the bug or the fix. diskinfo only tests reading, and you only showed a dd test using writing (to a file), so the problem is apparently only that writing to the second drive is slow. > =09what should be the right results? Swap the devices to see if it is a drive problem (unlikely with the same model of drive but... I have one system that apparently has worse timing on the secondary channel. This showed up as writes causing subsequent reads to be slow -- apparently the writes caused some errors and error correction as perfect except for slowing things down). Bruce --0-362250242-1119271740=:13863-- From owner-freebsd-performance@FreeBSD.ORG Mon Jun 20 14:43:44 2005 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 C627A16A41C for ; Mon, 20 Jun 2005 14:43:44 +0000 (GMT) (envelope-from scuba@centroin.com.br) Received: from gorgo.centroin.com.br (gorgo.centroin.com.br [200.225.63.128]) by mx1.FreeBSD.org (Postfix) with ESMTP id 41B4443D4C for ; Mon, 20 Jun 2005 14:43:43 +0000 (GMT) (envelope-from scuba@centroin.com.br) Received: from hypselo.centroin.com.br (hypselo.centroin.com.br [200.225.63.1]) by gorgo.centroin.com.br (8.12.10/8.12.9) with ESMTP id j5KEhRM3013326; Mon, 20 Jun 2005 11:43:35 -0300 (EST) Date: Mon, 20 Jun 2005 11:43:27 -0300 (EST) From: Sender: To: Bruce Evans In-Reply-To: <20050620222051.T13863@delplex.bde.org> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: freebsd-performance@FreeBSD.org Subject: Re: Slave IDE HDD not working in UDMA5 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, 20 Jun 2005 14:43:44 -0000 On Mon, 20 Jun 2005, Bruce Evans wrote: |On Thu, 16 Jun 2005 scuba@centroin.com.br wrote: | |> =09This was first posted on freebsd-question, but I could not find |> the solution yet. |> =09Maybe you could help me. | |Maybe a little. I don't use 5.4... =09It happens on 5.3 also. Not tested on 4.x. |> =09I=B4ve installed FreeBSD 5.4 on a new machine with the following |> hardware: |> |> =09Asus P4P800 SE (BIOS v. 1008) |> =092GB RAM ( 4x 512 DDR400 ) |> =092 HDD Samsung SP0802N (80GB 7200rpm ata-100) 80 pins cable. |> |> =09The HD were formated with newfs defaults, and the following |> results were the same using both as master (primary e secondary) or with= a |> master / slave (same interface). |> |> =09With diskinfo both performance are the same, but with "dd", the |> second disc (the slave or the secondary master), is always worst as if i= t |> were working in DMA2. | |I remember a commit to the ata driver to fix misprogramming of DMA timing |on an Intel chipset for devices and/or channels other than the first. I'm |not sure if 5.4 has the bug or the fix. =09It seems that the bug is still there. |diskinfo only tests reading, and you only showed a dd test using writing |(to a file), so the problem is apparently only that writing to the second |drive is slow. =09Right. |> =09what should be the right results? | |Swap the devices to see if it is a drive problem (unlikely with the |same model of drive but... I have one system that apparently has |worse timing on the secondary channel. This showed up as writes |causing subsequent reads to be slow -- apparently the writes caused |some errors and error correction as perfect except for slowing things |down). =09I=B4d already did it. It=B4s not a hardware problem. Always happen on the second drive, no matter which is it. - Marcelo From owner-freebsd-performance@FreeBSD.ORG Mon Jun 20 14:51:14 2005 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 E643C16A41C for ; Mon, 20 Jun 2005 14:51:13 +0000 (GMT) (envelope-from dsze@distrust.net) Received: from mail.distrust.net (mail.distrust.net [69.93.230.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id B3FBB43D1D for ; Mon, 20 Jun 2005 14:51:13 +0000 (GMT) (envelope-from dsze@distrust.net) Received: from eeyore.distrust.net (CPE00a0c978120d-CM00122570472e.cpe.net.cable.rogers.com [70.28.248.121]) (authenticated bits=0) by mail.distrust.net (8.13.3/8.13.3) with ESMTP id j5KEpCUs021026 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT) for ; Mon, 20 Jun 2005 09:51:13 -0500 (CDT) (envelope-from dsze@distrust.net) Message-Id: <6.2.1.2.2.20050620105116.06376688@wheresmymailserver.com> X-Mailer: QUALCOMM Windows Eudora Version 6.2.1.2 Date: Mon, 20 Jun 2005 10:51:30 -0400 To: performance@FreeBSD.org From: David Sze Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: ClamAV 0.85.1/946/Sun Jun 19 03:41:16 2005 on mail.distrust.net X-Virus-Status: Clean Cc: Subject: Re: FreeBSD MySQL still WAY slower than Linux 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, 20 Jun 2005 14:51:14 -0000 At 04:59 PM 19/06/2005 +0100, Robert Watson wrote this to All: >BTW, could you run 'file' on the Linux and FreeBSD MySQL binaries and >confirm that they're both either 32-bit i386 binaries, or 64-bit amd64 >binaries? I can no longer run tests on the machine because it's in production, but I will be re-running the tests on a different machine in the next few days, for reasons outlined below. They should both be amd64 binaries, I compiled from ports for FreeBSD and installs the x86_64 RPM for CentOS. >BTW, could you confirm that on 6.x, you're setting /etc/malloc.conf so >that it's not scrubbing memory on free()? In particular: > > ln -s jz /etc/malloc.conf > >as root. Most 6.x debugging features are set as part of the kernel >configuration, and your performance results suggest that you've caught >them all already, I think, but this one is user space. Also, make sure >you are compiling without INVARIANT_SUPPORT -- for packet send tests, I >find that even without INVARIANTS, I see a 4% hit for having >INVARIANT_SUPPORT in the kernel. I was using "ln -s aj /etc/malloc.conf" because I read somewhere that AJ were the only debugging options enabled in -CURRENT. I'll use "ajz" for the next set of tests. I had everything in the "Debugging for use in -current" section in GENERIC "nooptions"ed in my kernel config file, so INVARIANT_SUPPORT was gone. The reason I'm re-running the tests is due to things pointed out by various people last week. In particular: - ufs+soft_updates and ext3 are both async, but they guarantee consistency. So mounting the ext3 partition as sync and comparing it to ufs+soft_updates was meaningless. - Consistency guarantees are useless for databases because they have pretty much zero filesystem meta data updates. - MyISAM has no data durability guarantees, so using it on an async file system like ufs+soft_updates or ext3 is also meaningless (at least for my application, where writes are more common than reads, and durability is important). You can get durability with MyISAM by mounting sync, but write performance is horrible. - InnoDB has durability guarantees on an async filesystem (it uses one of fdatasync/fsync/O_SYNC/etc. at the appropriate times), so the results of the update-select super-smack benchmark look a lot different. I'll be re-running super-smack against an InnoDB table. Any additional requests for configurations to test, or other tweaking suggestions? This is what I'll be trying: FreeBSD/amd64 4.11-RELEASE, linuxthreads FreeBSD/amd64 5.4-RELEASE, libpthread FreeBSD/amd64 5.4-RELEASE, libpthread, process scope FreeBSD/amd64 6.0-CURRENT, libpthread FreeBSD/amd64 6.0-CURRENT, libpthread, process scope FreeBSD/amd64 6.0-CURRENT, libthr, system scope FreeBSD/amd64 6.0-CURRENT, libthr, process scope CentOS/amd64 4.0 The different threading libraries are more for completeness. In my last test I saw <10% difference between them on amd64. From owner-freebsd-performance@FreeBSD.ORG Mon Jun 20 15:05:59 2005 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 564AF16A41C for ; Mon, 20 Jun 2005 15:05:59 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [204.156.12.53]) by mx1.FreeBSD.org (Postfix) with ESMTP id 26F1C43D1F for ; Mon, 20 Jun 2005 15:05:59 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [204.156.12.50]) by cyrus.watson.org (Postfix) with ESMTP id AD70046B1E; Mon, 20 Jun 2005 11:05:58 -0400 (EDT) Date: Mon, 20 Jun 2005 16:08:45 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: David Sze In-Reply-To: <6.2.1.2.2.20050620102441.06372a70@mail.distrust.net> Message-ID: <20050620160522.C26664@fledge.watson.org> References: <746fd037f6ca8131a8fb8938f1e346e9@lonres.com> <20050610170537.GA67849@bibipentium.lonres.com> <20050611085604.J75625@fledge.watson.org> <20050616161506.GB28794@bibipentium.lonres.com> <6.2.1.2.2.20050617091736.05949298@mail.distrust.net> <20050619165349.U6413@fledge.watson.org> <6.2.1.2.2.20050620102441.06372a70@mail.distrust.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: performance@FreeBSD.org Subject: Re: FreeBSD MySQL still WAY slower than Linux 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, 20 Jun 2005 15:05:59 -0000 On Mon, 20 Jun 2005, David Sze wrote: > I'll be re-running super-smack against an InnoDB table. Any additional > requests for configurations to test, or other tweaking suggestions? > > This is what I'll be trying: > > FreeBSD/amd64 4.11-RELEASE, linuxthreads > FreeBSD/amd64 5.4-RELEASE, libpthread > FreeBSD/amd64 5.4-RELEASE, libpthread, process scope > FreeBSD/amd64 6.0-CURRENT, libpthread > FreeBSD/amd64 6.0-CURRENT, libpthread, process scope > FreeBSD/amd64 6.0-CURRENT, libthr, system scope > FreeBSD/amd64 6.0-CURRENT, libthr, process scope > CentOS/amd64 4.0 > > The different threading libraries are more for completeness. In my last > test I saw <10% difference between them on amd64. I realize every additional variation increases the testing load, but I'd be interested in seeing linuxthreads performance on 5.x/6.x also. While we've worked hard to improve native threading, linuxthreading remains fully functional, and given that MySQL may well be being optimized based on assumptions regarding the Linux threading model, it could well be linuxthreads comes in ahead on recent versions. You probably did this in a prior e-mail but I may have missed it -- could you forward me a copy of the 6.x kernel dmesg via private e-mail? Thanks, Robert N M Watson From owner-freebsd-performance@FreeBSD.ORG Mon Jun 20 15:15:48 2005 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 60EFA16A41C; Mon, 20 Jun 2005 15:15:48 +0000 (GMT) (envelope-from dsze@mail.distrust.net) Received: from mail.distrust.net (mail.distrust.net [69.93.230.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2FF9243D1F; Mon, 20 Jun 2005 15:15:48 +0000 (GMT) (envelope-from dsze@mail.distrust.net) Received: from mail.distrust.net (localhost [127.0.0.1]) by mail.distrust.net (8.13.3/8.13.3) with ESMTP id j5KFFl1F021181; Mon, 20 Jun 2005 10:15:47 -0500 (CDT) (envelope-from dsze@mail.distrust.net) Received: (from dsze@localhost) by mail.distrust.net (8.13.3/8.13.3/Submit) id j5KFFl1a021180; Mon, 20 Jun 2005 10:15:47 -0500 (CDT) (envelope-from dsze) Date: Mon, 20 Jun 2005 10:15:47 -0500 From: David Sze To: Robert Watson Message-ID: <20050620151547.GA21151@mail.distrust.net> References: <746fd037f6ca8131a8fb8938f1e346e9@lonres.com> <20050610170537.GA67849@bibipentium.lonres.com> <20050611085604.J75625@fledge.watson.org> <20050616161506.GB28794@bibipentium.lonres.com> <6.2.1.2.2.20050617091736.05949298@mail.distrust.net> <20050619165349.U6413@fledge.watson.org> <6.2.1.2.2.20050620102441.06372a70@mail.distrust.net> <20050620160522.C26664@fledge.watson.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20050620160522.C26664@fledge.watson.org> User-Agent: Mutt/1.4.2.1i X-Virus-Scanned: ClamAV 0.85.1/946/Sun Jun 19 03:41:16 2005 on mail.distrust.net X-Virus-Status: Clean Cc: performance@freebsd.org Subject: Re: FreeBSD MySQL still WAY slower than Linux 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, 20 Jun 2005 15:15:48 -0000 On Mon, Jun 20, 2005 at 04:08:45PM +0100, Robert Watson wrote: > > I realize every additional variation increases the testing load, but I'd > be interested in seeing linuxthreads performance on 5.x/6.x also. While > we've worked hard to improve native threading, linuxthreading remains > fully functional, and given that MySQL may well be being optimized based > on assumptions regarding the Linux threading model, it could well be > linuxthreads comes in ahead on recent versions. linuxthreads actually doesn't compile for amd64. I can try i386 versions of 5.4 and 6.0 too; that will delay the results by a couple more days though (I'm doing this in my spare time, though using work hardware). From owner-freebsd-performance@FreeBSD.ORG Mon Jun 20 20:54:17 2005 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 8936B16A41C for ; Mon, 20 Jun 2005 20:54:17 +0000 (GMT) (envelope-from mikej@rogers.com) Received: from smtp104.rog.mail.re2.yahoo.com (smtp104.rog.mail.re2.yahoo.com [206.190.36.82]) by mx1.FreeBSD.org (Postfix) with SMTP id 25CC943D49 for ; Mon, 20 Jun 2005 20:54:16 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 88031 invoked from network); 20 Jun 2005 20:54:06 -0000 Received: from unknown (HELO 172.16.0.1) (mikej@69.193.222.195 with login) by smtp104.rog.mail.re2.yahoo.com with SMTP; 20 Jun 2005 20:54:06 -0000 Received: from 172.16.0.199 (SquirrelMail authenticated user mikej) by 172.16.0.1 with HTTP; Mon, 20 Jun 2005 16:54:04 -0400 (EDT) Message-ID: <1690.172.16.0.199.1119300844.squirrel@172.16.0.1> In-Reply-To: <6.2.1.2.2.20050620105116.06376688@wheresmymailserver.com> References: <6.2.1.2.2.20050620105116.06376688@wheresmymailserver.com> Date: Mon, 20 Jun 2005 16:54:04 -0400 (EDT) From: "Mike Jakubik" To: "David Sze" User-Agent: SquirrelMail/1.5.1 [CVS] MIME-Version: 1.0 Content-Type: text/plain;charset=iso-8859-1 Content-Transfer-Encoding: 8bit Cc: performance@freebsd.org Subject: Re: FreeBSD MySQL still WAY slower than Linux 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, 20 Jun 2005 20:54:17 -0000 On Mon, June 20, 2005 10:51 am, David Sze said: > > I'll be re-running super-smack against an InnoDB table. Any additional > requests for configurations to test, or other tweaking suggestions? Any chance you could compare performance on MySQL 4.0 and 4.1 while you're at it? From owner-freebsd-performance@FreeBSD.ORG Tue Jun 21 02:57:30 2005 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 D5A6316A41C for ; Tue, 21 Jun 2005 02:57:30 +0000 (GMT) (envelope-from jd@philemon.async.caltech.edu) Received: from philemon.async.caltech.edu (philemon.async.caltech.edu [131.215.39.102]) by mx1.FreeBSD.org (Postfix) with ESMTP id A3ABD43D49 for ; Tue, 21 Jun 2005 02:57:30 +0000 (GMT) (envelope-from jd@philemon.async.caltech.edu) Received: from philemon.async.caltech.edu (localhost.caltech.edu [127.0.0.1]) by philemon.async.caltech.edu (8.13.1/8.13.1) with ESMTP id j5L2vSn0026357 for ; Mon, 20 Jun 2005 19:57:28 -0700 (PDT) (envelope-from jd@philemon.async.caltech.edu) Received: (from jd@localhost) by philemon.async.caltech.edu (8.13.3/8.13.1/Submit) id j5L2vREE026356 for freebsd-performance@freebsd.org; Mon, 20 Jun 2005 19:57:27 -0700 (PDT) (envelope-from jd) Date: Mon, 20 Jun 2005 19:57:27 -0700 From: eng@donut.ugcs.caltech.edu To: freebsd-performance@freebsd.org Message-ID: <20050621025727.GI24844@philemon.async.caltech.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline X-Mailman-Approved-At: Tue, 21 Jun 2005 12:52:18 +0000 Subject: sustained sequential disk IO runs interactivity into the ground 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, 21 Jun 2005 02:57:30 -0000 I was doing a dd of dev/zero into a file on a UFS2 filesystem (softupdates disabled) on a clean 5.4-R system. an exec of top took approximately 30 seconds to complete and then revealed sys: 13% and idle: 87% quit, repeat five times, same delay, same numbers each time. FreeBSD 4.11 managed this with only a minor interactivity hit. What's going on here? Any ideas? From owner-freebsd-performance@FreeBSD.ORG Tue Jun 21 13:08:21 2005 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 6BFAF16A41C for ; Tue, 21 Jun 2005 13:08:21 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (www1.multiplay.co.uk [212.42.16.7]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0AAA743D1F for ; Tue, 21 Jun 2005 13:08:20 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [212.42.16.7]) (MDaemon.PRO.v8.0.2.R) with ESMTP id md50001543885.msg for ; Tue, 21 Jun 2005 14:02:22 +0100 Message-ID: <00fe01c57662$2ac82700$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: , References: <20050621025727.GI24844@philemon.async.caltech.edu> Date: Tue, 21 Jun 2005 14:07:20 +0100 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 6.00.2900.2527 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 X-Spam-Processed: multiplay.co.uk, Tue, 21 Jun 2005 14:02:22 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Tue, 21 Jun 2005 14:02:23 +0100 Cc: Subject: Re: sustained sequential disk IO runs interactivity into the ground 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, 21 Jun 2005 13:08:21 -0000 Have you tried the vfs patch posted a few weeks ago? Steve / K ----- Original Message ----- From: >I was doing a dd of dev/zero into a file on a UFS2 filesystem > (softupdates disabled) on a clean 5.4-R system. > > an exec of top took approximately 30 seconds to complete > and then revealed sys: 13% and idle: 87% > > quit, repeat five times, same delay, same numbers each time. > > FreeBSD 4.11 managed this with only a minor interactivity > hit. > > What's going on here? Any ideas? ================================================ 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 (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Tue Jun 21 13:42:16 2005 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 5C1EB16A41C for ; Tue, 21 Jun 2005 13:42:16 +0000 (GMT) (envelope-from mike@sentex.net) Received: from smarthost1.sentex.ca (smarthost1.sentex.ca [64.7.153.18]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1A68043D48 for ; Tue, 21 Jun 2005 13:42:15 +0000 (GMT) (envelope-from mike@sentex.net) Received: from pumice3.sentex.ca (pumice3.sentex.ca [64.7.153.26]) by smarthost1.sentex.ca (8.13.3/8.13.3) with ESMTP id j5LDfllG016502 for ; Tue, 21 Jun 2005 09:41:47 -0400 (EDT) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by pumice3.sentex.ca (8.13.3/8.13.3) with ESMTP id j5LDgE2O015689; Tue, 21 Jun 2005 09:42:14 -0400 (EDT) (envelope-from mike@sentex.net) Received: from simian.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.13.3/8.13.3) with ESMTP id j5LDg8sG000532 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Tue, 21 Jun 2005 09:42:08 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <6.2.1.2.0.20050621092842.05c8cd30@64.7.153.2> X-Mailer: QUALCOMM Windows Eudora Version 6.2.1.2 Date: Tue, 21 Jun 2005 09:42:48 -0400 To: eng@donut.ugcs.caltech.edu, freebsd-performance@freebsd.org From: Mike Tancsa In-Reply-To: <20050621025727.GI24844@philemon.async.caltech.edu> References: <20050621025727.GI24844@philemon.async.caltech.edu> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by amavisd-new X-Scanned-By: MIMEDefang 2.51 on 64.7.153.18 X-Scanned-By: MIMEDefang 2.51 on 64.7.153.26 Cc: Subject: Re: sustained sequential disk IO runs interactivity into the ground 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, 21 Jun 2005 13:42:16 -0000 At 10:57 PM 20/06/2005, eng@donut.ugcs.caltech.edu wrote: >I was doing a dd of dev/zero into a file on a UFS2 filesystem >(softupdates disabled) on a clean 5.4-R system. I see the same issue on RELENG_5 with IDE disk. However, on FreeBSD nfs.sentex.ca 6.0-CURRENT FreeBSD 6.0-CURRENT #1: Fri Jun 17 No such issue against an IDE drive as well as an ARECA RAID5 array. The box is quite responsive while blasting the disks Also just tested against a RELENG_5 box and a twe RAID1 array and no problems. The system is totally responsive while doing So it might be the IDE drivers on RELENG_5 ? Perhaps try sos@freebsd.org's backport of the CURRENT IDE drivers to stable. ---Mike From owner-freebsd-performance@FreeBSD.ORG Thu Jun 23 10:20:03 2005 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 969F416A41C for ; Thu, 23 Jun 2005 10:20:03 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (www1.multiplay.co.uk [212.42.16.7]) by mx1.FreeBSD.org (Postfix) with ESMTP id 38B7843D1F for ; Thu, 23 Jun 2005 10:20:00 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([217.41.249.254]) by multiplay.co.uk (multiplay.co.uk [212.42.16.7]) (MDaemon.PRO.v8.0.2.R) with ESMTP id md50001549525.msg for ; Thu, 23 Jun 2005 11:14:27 +0100 Message-ID: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> From: "Steven Hartland" To: Date: Thu, 23 Jun 2005 11:19:26 +0100 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 6.00.2900.2527 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 X-Spam-Processed: multiplay.co.uk, Thu, 23 Jun 2005 11:14:27 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 217.41.249.254 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Thu, 23 Jun 2005 11:14:27 +0100 Subject: Fibre Gig card recommendations? 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: Thu, 23 Jun 2005 10:20:03 -0000 Can anyone give me a Fibre Gig card recommendations PCI-X based that they have used in FreeBSD 5.4 machines preferably? 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 (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Thu Jun 23 14:46:17 2005 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 1AA1D16A41C for ; Thu, 23 Jun 2005 14:46:17 +0000 (GMT) (envelope-from steve@pepcross.com) Received: from anchor-post-36.mail.demon.net (anchor-post-36.mail.demon.net [194.217.242.86]) by mx1.FreeBSD.org (Postfix) with ESMTP id 943E143D49 for ; Thu, 23 Jun 2005 14:46:16 +0000 (GMT) (envelope-from steve@pepcross.com) Received: from mail.lonres.com ([194.70.153.187]) by anchor-post-36.mail.demon.net with esmtp (Exim 4.42) id 1DlSxg-000IIt-MW; Thu, 23 Jun 2005 14:45:53 +0000 Received: from pepcross.com (bibipentium.lonres.com [10.10.10.225]) by mail.lonres.com (Postfix) with SMTP id B0A912E09F; Thu, 23 Jun 2005 15:45:48 +0100 (BST) Received: by pepcross.com (sSMTP sendmail emulation); Thu, 23 Jun 2005 15:46:11 +0100 Date: Thu, 23 Jun 2005 15:46:11 +0100 From: Steve Roome To: David Sze Message-ID: <20050623144611.GA64879@bibipentium.lonres.com> References: <6.2.1.2.2.20050620105116.06376688@wheresmymailserver.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <6.2.1.2.2.20050620105116.06376688@wheresmymailserver.com> User-Agent: Mutt/1.4.2.1i Cc: performance@FreeBSD.org Subject: Re: FreeBSD MySQL still WAY slower than Linux 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: Thu, 23 Jun 2005 14:46:17 -0000 On Mon, Jun 20, 2005 at 10:51:30AM -0400, David Sze wrote: > This is what I'll be trying: > > FreeBSD/amd64 4.11-RELEASE, linuxthreads > FreeBSD/amd64 5.4-RELEASE, libpthread > FreeBSD/amd64 5.4-RELEASE, libpthread, process scope > FreeBSD/amd64 6.0-CURRENT, libpthread > FreeBSD/amd64 6.0-CURRENT, libpthread, process scope > FreeBSD/amd64 6.0-CURRENT, libthr, system scope > FreeBSD/amd64 6.0-CURRENT, libthr, process scope > CentOS/amd64 4.0 > > The different threading libraries are more for completeness. In my last > test I saw <10% difference between them on amd64. Well, I finally got some tests out for FreeBSD/i386 with -current, Here we go with a bunch of results of FreeBSD 6 with mysql and different threading libraries, as for you, there's sadly not enough in it so far. Maybe I need to tune a whole bunch of stuff I've missed ? This is with a fairly basic build of mysql (dynamic and local data directories specified, IMHO the options have made not a lot of difference so far in changing these numbers.) The test run is always: date foreach f (1 2 3 4 5) { /data/supersmack-1.3/bin/super-smack select-key.smack 50 1000 | grep select_index } date with vmstat -systat 35 started before each count and the screen grabbed at the end (each run takes just under 30 seconds and there's no other considerable load on the, so vmstat is a rough, but not too bad guide as to what's going on.) Roughly speaking: pthread as system scope, process scope or whatever out of the box is, is about ~16500 queries per second. libthr, as it comes out of the box is about 17600 qps. i.e. on 6.0, with a plain vanilla setup libthr+mysql is about 6% faster than plain pthreads for this test. I was kind of hoping for more, any suggested tweaks as this is still the same speed for me as FreeBSD 5. I've attached the config file I've used, make.conf and a few other bits and bobs. The full results are below: Steve Roome pthread: 6tst1: root@unoctbium 3 1 # ldd /data/mysql/libexec/mysqld 6tst1: /data/mysql/libexec/mysqld: 6tst1: libz.so.2 => /lib/libz.so.2 (0x884b9000) 6tst1: libwrap.so.3 => /usr/lib/libwrap.so.3 (0x884c9000) 6tst1: libcrypt.so.2 => /lib/libcrypt.so.2 (0x884d0000) 6tst1: libstdc++.so.4 => /usr/lib/libstdc++.so.4 (0x884e9000) 6tst1: libm.so.3 => /lib/libm.so.3 (0x885b8000) 6tst1: libpthread.so.1 => /usr/lib/libpthread.so.1 (0x885ce000) 6tst1: libc.so.6 => /lib/libc.so.6 (0x885f5000) 6tst1: 6tst1: root@unoctbium 27 0 # foreach f (1 2 3 4 5) { /data/supersmack-1.3/bin/super-smack select-key.smack 50 1000|grep select_index } 6tst1: select_index 100000 4 0 17745.75 6tst1: select_index 100000 2 0 16793.02 6tst1: select_index 100000 3 0 16461.78 6tst1: select_index 100000 2 0 16426.02 6tst1: select_index 100000 4 0 16363.65 6tst1: 6tst1: 2 users Load 19.18 7.60 3.44 23 Jun 15:07 6tst1: 6tst1: Mem:KB REAL VIRTUAL VN PAGER SWAP PAGER 6tst1: Tot Share Tot Share Free in out in out 6tst1: Act 1488784 3588 1536232 4432 186704 count 6tst1: All 3328012 5692 17474532 7296 pages 6tst1: Interrupts 6tst1: Proc:r p d s w Csw Trp Sys Int Sof Flt 287 cow 4003 total 6tst1: 71 31592 404 526k 15115712 372 200564 wire 1: atkb 6tst1: 1487616 act 6: fdc0 6tst1: 46.5%Sys 0.0%Intr 40.1%User 0.0%Nice 13.4%Idl 1467508 inact 13: npx 6tst1: | | | | | | | | | | 174776 cache 14: ata 6tst1: =======================>>>>>>>>>>>>>>>>>>>> 11928 free 46: amr 6tst1: daefr 1 64: em0 6tst1: Namei Name-cache Dir-cache 322 prcfr 2001 lapic0: ti 6tst1: Calls hits % hits % react 2001 lapic6: ti 6tst1: 1734 1734 100 pdwake 6tst1: 50 zfod 604 pdpgs 6tst1: Disks amrd0 amrd1 pass0 27 ofod intrn 6tst1: KB/t 16.00 0.00 0.00 54 %slo-z 114464 buf 6tst1: tps 1 0 0 401 tfree 12 dirtybuf 6tst1: MB/s 0.01 0.00 0.00 100000 desiredvnodes 6tst1: % busy 0 0 0 51030 numvnodes 6tst1: 24175 freevnodes 6tst1: ------------------------------------------------------------------------ 6tst2: pthread system scope 6tst2: LIBPTHREAD_SYSTEM_SCOPE=yes sh /usr/local/etc/rc.d/420.mysql-server.sh start 6tst2: 6tst2: Thu 23 Jun 2005 15:09:54 BST 6tst2: select_index 100000 4 0 16409.75 6tst2: select_index 100000 2 0 16385.46 6tst2: select_index 100000 3 0 16419.39 6tst2: select_index 100000 2 0 16449.73 6tst2: select_index 100000 7 0 16308.51 6tst2: Thu 23 Jun 2005 15:10:24 BST 6tst2: 6tst2: 6tst2: 2 users Load 20.93 9.89 4.92 23 Jun 15:10 6tst2: 6tst2: Mem:KB REAL VIRTUAL VN PAGER SWAP PAGER 6tst2: Tot Share Tot Share Free in out in out 6tst2: Act 1488732 3588 1536072 4432 186336 count 6tst2: All 3327784 5696 17474672 7296 pages 6tst2: Interrupts 6tst2: Proc:r p d s w Csw Trp Sys Int Sof Flt 293 cow 4004 total 6tst2: 75 30143 408 557k 13014975 377 200968 wire 1: atkb 6tst2: 1487560 act 6: fdc0 6tst2: 47.1%Sys 0.0%Intr 40.4%User 0.0%Nice 12.4%Idl 1467528 inact 13: npx 6tst2: | | | | | | | | | | 174284 cache 14: ata 6tst2: ========================>>>>>>>>>>>>>>>>>>>> 12052 free 1 46: amr 6tst2: daefr 1 64: em0 6tst2: Namei Name-cache Dir-cache 329 prcfr 2001 lapic0: ti 6tst2: Calls hits % hits % react 2001 lapic6: ti 6tst2: 1905 1905 100 pdwake 6tst2: 52 zfod pdpgs 6tst2: Disks amrd0 amrd1 pass0 28 ofod intrn 6tst2: KB/t 14.11 0.00 0.00 54 %slo-z 114464 buf 6tst2: tps 1 0 0 381 tfree 21 dirtybuf 6tst2: MB/s 0.01 0.00 0.00 100000 desiredvnodes 6tst2: % busy 0 0 0 51031 numvnodes 6tst2: 24179 freevnodes ------------------------------------------------------------------------ 6tst3: pthread process scope 6tst3: LIBPTHREAD_PROCESS_SCOPE=yes sh /usr/local/etc/rc.d/420.mysql-server.sh start 6tst3: 6tst3: 6tst3: Thu 23 Jun 2005 15:14:34 BST 6tst3: select_index 100000 6 0 15782.35 6tst3: select_index 100000 12 2 16668.64 6tst3: select_index 100000 11 2 16667.71 6tst3: select_index 100000 12 3 16605.03 6tst3: select_index 100000 12 2 16620.37 6tst3: Thu 23 Jun 2005 15:15:05 BST 6tst3: 6tst3: 2 users Load 3.61 5.05 3.99 23 Jun 15:15 6tst3: 6tst3: Mem:KB REAL VIRTUAL VN PAGER SWAP PAGER 6tst3: Tot Share Tot Share Free in out in out 6tst3: Act 1488776 3588 1536232 4432 185820 count 6tst3: All 3327496 5696 17475168 7296 pages 6tst3: Interrupts 6tst3: Proc:r p d s w Csw Trp Sys Int Sof Flt 289 cow 4004 total 6tst3: 29 3191415496 392k 11614723 372 201436 wire 1: atkb 6tst3: 1487600 act 6: fdc0 6tst3: 47.3%Sys 0.0%Intr 39.5%User 0.0%Nice 13.2%Idl 1467536 inact 13: npx 6tst3: | | | | | | | | | | 173480 cache 14: ata 6tst3: ========================>>>>>>>>>>>>>>>>>>> 12340 free 1 46: amr 6tst3: daefr 1 64: em0 6tst3: Namei Name-cache Dir-cache 326 prcfr 2001 lapic0: ti 6tst3: Calls hits % hits % react 2001 lapic6: ti 6tst3: 1877 1877 100 pdwake 6tst3: 52 zfod pdpgs 6tst3: Disks amrd0 amrd1 pass0 30 ofod intrn 6tst3: KB/t 13.24 0.00 0.00 57 %slo-z 114464 buf 6tst3: tps 1 0 0 378 tfree 26 dirtybuf 6tst3: MB/s 0.01 0.00 0.00 100000 desiredvnodes 6tst3: % busy 0 0 0 51032 numvnodes ------------------------------------------------------------------------ 6tst4: pthread, libthr 6tst4: 6tst4: root@unoctbium 12 0 # ldd /data/mysql/libexec/mysqld 6tst4: /data/mysql/libexec/mysqld: 6tst4: libz.so.2 => /lib/libz.so.2 (0x884b9000) 6tst4: libwrap.so.3 => /usr/lib/libwrap.so.3 (0x884c9000) 6tst4: libcrypt.so.2 => /lib/libcrypt.so.2 (0x884d0000) 6tst4: libstdc++.so.4 => /usr/lib/libstdc++.so.4 (0x884e9000) 6tst4: libm.so.3 => /lib/libm.so.3 (0x885b8000) 6tst4: libpthread.so.1 => /usr/lib/libthr.so.1 (0x885ce000) 6tst4: libc.so.6 => /lib/libc.so.6 (0x885e0000) 6tst4: 6tst4: root@unoctbium 37 0 # cat /etc/libmap.conf 6tst4: [mysqld] 6tst4: libpthread.so.1 libthr.so.1 6tst4: libpthread.so libthr.so 6tst4: 6tst4: 6tst4: Thu 23 Jun 2005 15:20:12 BST 6tst4: select_index 100000 6 1 17613.29 6tst4: select_index 100000 5 0 17589.25 6tst4: select_index 100000 8 0 17645.14 6tst4: select_index 100000 3 0 17712.81 6tst4: select_index 100000 4 0 17620.33 6tst4: 6tst4: Thu 23 Jun 2005 15:20:41 BST 6tst4: 6tst4: 6tst4: 2 users Load 28.65 11.20 6.37 23 Jun 15:20 6tst4: 6tst4: Mem:KB REAL VIRTUAL VN PAGER SWAP PAGER 6tst4: Tot Share Tot Share Free in out in out 6tst4: Act 1457916 3512 1504052 4360 215256 count 6tst4: All 3298108 5620 17443856 7224 pages 6tst4: Interrupts 6tst4: Proc:r p d s w Csw Trp Sys Int Sof Flt 316 cow 4004 total 6tst4: 75 29760 427 501k 12514703 397 201964 wire 1: atkb 6tst4: 1456924 act 6: fdc0 6tst4: 44.7%Sys 0.0%Intr 36.6%User 0.0%Nice 18.6%Idl 1468236 inact 13: npx 6tst4: | | | | | | | | | | 173492 cache 14: ata 6tst4: ======================>>>>>>>>>>>>>>>>>>> 41764 free 1 46: amr 6tst4: daefr 1 64: em0 6tst4: Namei Name-cache Dir-cache 352 prcfr 2001 lapic0: ti 6tst4: Calls hits % hits % react 2001 lapic6: ti 6tst4: 1722 1722 100 pdwake 6tst4: 51 zfod pdpgs 6tst4: Disks amrd0 amrd1 pass0 23 ofod intrn 6tst4: KB/t 14.61 0.00 0.00 44 %slo-z 114464 buf 6tst4: tps 1 0 0 397 tfree 11 dirtybuf 6tst4: MB/s 0.01 0.00 0.00 100000 desiredvnodes 6tst4: % busy 0 0 0 51117 numvnodes From owner-freebsd-performance@FreeBSD.ORG Thu Jun 23 14:50:13 2005 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 EAEED16A41C for ; Thu, 23 Jun 2005 14:50:13 +0000 (GMT) (envelope-from steve@pepcross.com) Received: from anchor-post-34.mail.demon.net (anchor-post-34.mail.demon.net [194.217.242.92]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8CC3B43D55 for ; Thu, 23 Jun 2005 14:50:13 +0000 (GMT) (envelope-from steve@pepcross.com) Received: from mail.lonres.com ([194.70.153.187]) by anchor-post-34.mail.demon.net with esmtp (Exim 4.42) id 1DlT1u-000O95-DG; Thu, 23 Jun 2005 14:50:11 +0000 Received: from pepcross.com (bibipentium.lonres.com [10.10.10.225]) by mail.lonres.com (Postfix) with SMTP id A1FC12E07C; Thu, 23 Jun 2005 15:50:08 +0100 (BST) Received: by pepcross.com (sSMTP sendmail emulation); Thu, 23 Jun 2005 15:50:31 +0100 Date: Thu, 23 Jun 2005 15:50:31 +0100 From: Steve Roome To: David Sze Message-ID: <20050623145031.GB64879@bibipentium.lonres.com> References: <6.2.1.2.2.20050620105116.06376688@wheresmymailserver.com> <20050623144611.GA64879@bibipentium.lonres.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20050623144611.GA64879@bibipentium.lonres.com> User-Agent: Mutt/1.4.2.1i Cc: performance@FreeBSD.org Subject: Re: FreeBSD MySQL still WAY slower than Linux 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: Thu, 23 Jun 2005 14:50:14 -0000 Oops, here's what I was supposed to "attach" to the email with test results in it. Sorry about that, Steve Roome ######################################################################## /etc/make.conf ######################################################################## WITHOUT_X11=yes WITHOUT_NLS=yes CFLAGS?=-O3 -pipe CPUTYPE?=p4 KERNCONF?=PE2650_i386_steve NO_PROFILE=true MASTER_SITE_BACKUP?= ftp://ftp.uk.freebsd.org/pub/FreeBSD/ports/distfiles/${DIST_SUBDIR}/ MASTER_SITE_OVERRIDE?= ${MASTER_SITE_BACKUP} SUP_UPDATE=yes SUP=/usr/local/bin/cvsup SUPFLAGS=-g -L 2 SUPHOST=cvsup.uk.FreeBSD.org SUPFILE=/usr/src/supfile PORTSSUPFILE=/usr/ports/ports-supfile # added by use.perl 2005-06-23 10:21:11 PERL_VER=5.8.6 PERL_VERSION=5.8.6 ######################################################################## # Kernel configuration ######################################################################## # $FreeBSD: src/sys/i386/conf/GENERIC,v 1.413.2.8 2004/10/24 17:42:08 scottl Exp $ machine i386 cpu I686_CPU ident PE2650_i386_1 options MAXDSIZ=(2048UL*1024*1024) options SCHED_4BSD # 4BSD scheduler options INET # InterNETworking options FFS # Berkeley Fast Filesystem options SOFTUPDATES # Enable FFS soft updates support options UFS_ACL # Support for access control lists options UFS_DIRHASH # Improve performance on big directories # can be dynamically loaded: options NFSCLIENT # Network Filesystem Client # can be dynamically loaded: options NFSSERVER # Network Filesystem Server # can be dynamically loaded: options MSDOSFS # MSDOS Filesystem # can be dynamically loaded: options CD9660 # ISO 9660 Filesystem # can be dynamically loaded: options PROCFS # Process filesystem (requires PSEUDOFS) options PSEUDOFS # Pseudo-filesystem framework options GEOM_GPT # GUID Partition Tables. options COMPAT_43 # Compatible with BSD 4.3 [KEEP THIS!] options COMPAT_FREEBSD4 # Compatible with FreeBSD4 options SCSI_DELAY=1000 # Delay (in ms) before probing SCSI options KTRACE # ktrace(1) support options SYSVSHM # SYSV-style shared memory options SYSVMSG # SYSV-style message queues options SYSVSEM # SYSV-style semaphores options _KPOSIX_PRIORITY_SCHEDULING # POSIX P1003_1B real-time extensions options KBD_INSTALL_CDEV # install a CDEV entry in /dev options ADAPTIVE_GIANT # Giant mutex is adaptive. options SMP device apic # I/O APIC device isa device pci device fdc device ata device atapicd # ATAPI CDROM drives options ATA_STATIC_ID # Static device numbering device scbus # SCSI bus (required for SCSI) # can be dynamically loaded: device ch # SCSI media changers device da # Direct Access (disks) # can be dynamically loaded: device sa # Sequential Access (tape etc) device pass # Passthrough device (direct SCSI access) # can be dynamically loaded: device ses # SCSI Environmental Services (and SAF-TE) device aac # Adaptec FSA RAID device aacp # SCSI passthrough for aac (requires CAM) device atkbdc # AT keyboard controller device atkbd # AT keyboard device vga # VGA video card driver device sc # can be dynamically loaded: device agp # support several AGP chipsets device npx device sio # 8250, 16[45]50 based serial ports device miibus # MII bus support device bge # Broadcom BCM570xx Gigabit Ethernet device loop # Network loopback device mem # Memory and kernel memory devices device io # I/O device device random # Entropy device device ether # Ethernet support # can be dynamically loaded: device ppp # Kernel PPP # can be dynamically loaded: device tun # Packet tunnel. device pty # Pseudo-ttys (telnet etc) device md # Memory "disks" device gif # IPv6 and IPv4 tunneling device bpf # Berkeley packet filter device amr device em ######################################################################## # dmesg output ######################################################################## Copyright (c) 1992-2005 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 6.0-CURRENT #2: Wed Jun 22 17:30:47 BST 2005 root@unoctbium.lonres.com:/usr/obj/usr/src/sys/PE2650_i386_steve ACPI APIC Table: Timecounter "i8254" frequency 1193182 Hz quality 0 CPU: Intel(R) Xeon(TM) CPU 2.80GHz (2793.01-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0xf34 Stepping = 4 Features=0xbfebfbff Features2=0x441d> real memory = 3489398784 (3327 MB) avail memory = 3419168768 (3260 MB) FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs cpu0 (BSP): APIC ID: 0 cpu1 (AP): APIC ID: 6 ioapic0: Changing APIC ID to 7 ioapic1: Changing APIC ID to 8 ioapic1: WARNING: intbase 32 != expected base 24 ioapic2: Changing APIC ID to 9 ioapic2: WARNING: intbase 64 != expected base 56 ioapic3: Changing APIC ID to 10 ioapic3: WARNING: intbase 96 != expected base 88 ioapic0 irqs 0-23 on motherboard ioapic1 irqs 32-55 on motherboard ioapic2 irqs 64-87 on motherboard ioapic3 irqs 96-119 on motherboard npx0: [FAST] npx0: on motherboard npx0: INT 16 interface acpi0: on motherboard acpi0: Power Button (fixed) pci_link0: irq 7 on acpi0 pci_link1: irq 5 on acpi0 pci_link2: irq 10 on acpi0 pci_link3: on acpi0 pci_link4: on acpi0 pci_link5: on acpi0 pci_link6: on acpi0 pci_link7: on acpi0 Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 acpi_timer0: <24-bit timer at 3.579545MHz> port 0x808-0x80b on acpi0 cpu0: on acpi0 cpu1: on acpi0 pcib0: port 0xcf8-0xcff on acpi0 pci0: on pcib0 pcib1: at device 2.0 on pci0 pci1: on pcib1 pcib2: at device 0.0 on pci1 pci2: on pcib2 amr0: mem 0xd80f0000-0xd80fffff,0xdfec0000-0xdfefffff irq 46 at device 14.0 on pci2 amr0: Firmware 513O, BIOS H418, 256MB RAM pcib3: at device 0.2 on pci1 pci3: on pcib3 pcib4: at device 4.0 on pci0 pci4: on pcib4 pcib5: at device 5.0 on pci0 pci5: on pcib5 pcib6: at device 0.0 on pci5 pci6: on pcib6 em0: port 0xecc0-0xecff mem 0xdfbe0000-0xdfbfffff irq 64 at device 7.0 on pci6 em0: Ethernet address: 00:11:43:33:9c:e3 em0: Speed:N/A Duplex:N/A pcib7: at device 0.2 on pci5 pci7: on pcib7 em1: port 0xdcc0-0xdcff mem 0xdf9e0000-0xdf9fffff irq 65 at device 8.0 on pci7 em1: Ethernet address: 00:11:43:33:9c:e4 em1: Speed:N/A Duplex:N/A pcib8: at device 6.0 on pci0 pci8: on pcib8 pcib9: at device 0.0 on pci8 pci9: on pcib9 pcib10: at device 0.2 on pci8 pci10: on pcib10 pcib11: at device 30.0 on pci0 pci11: on pcib11 pci11: at device 13.0 (no driver attached) isab0: at device 31.0 on pci0 isa0: on isab0 atapci0: port 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0xfc00-0xfc0f at device 31.1 on pci0 ata0: on atapci0 ata1: on atapci0 fdc0: port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on acpi0 fdc0: [FAST] fd0: <1440-KB 3.5" drive> on fdc0 drive 0 atkbdc0: port 0x60,0x64 irq 1 on acpi0 atkbd0: irq 1 on atkbdc0 kbd0 at atkbd0 atkbd0: [GIANT-LOCKED] sio0: <16550A-compatible COM port> port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 sio0: type 16550A orm0: at iomem 0xc0000-0xcafff,0xec000-0xeffff on isa0 sc0: at flags 0x100 on isa0 sc0: VGA <16 virtual consoles, flags=0x300> vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 sio1: configured irq 3 not in bitmap of probed irqs 0 sio1: port may not be enabled Timecounters tick every 1.000 msec acd0: CDROM at ata0-master UDMA33 pass0 at amr0 bus 0 target 6 lun 0 pass0: Fixed Processor SCSI-2 device amrd0: on amr0 amrd0: 69360MB (142049280 sectors) RAID 5 (optimal) amrd1: on amr0 amrd1: 69360MB (142049280 sectors) RAID 5 (optimal) SMP: AP CPU #1 Launched! Trying to mount root from ufs:/dev/amrd0s1a em0: link state changed to UP From owner-freebsd-performance@FreeBSD.ORG Thu Jun 23 14:50:29 2005 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 C6F1D16A41C for ; Thu, 23 Jun 2005 14:50:29 +0000 (GMT) (envelope-from steve@pepcross.com) Received: from anchor-post-33.mail.demon.net (anchor-post-33.mail.demon.net [194.217.242.91]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6A80B43D55 for ; Thu, 23 Jun 2005 14:50:29 +0000 (GMT) (envelope-from steve@pepcross.com) Received: from mail.lonres.com ([194.70.153.187]) by anchor-post-33.mail.demon.net with esmtp (Exim 4.42) id 1DlT25-0002VC-Ai; Thu, 23 Jun 2005 14:50:23 +0000 Received: from pepcross.com (bibipentium.lonres.com [10.10.10.225]) by mail.lonres.com (Postfix) with SMTP id AB7312E09E; Thu, 23 Jun 2005 15:50:18 +0100 (BST) Received: by pepcross.com (sSMTP sendmail emulation); Thu, 23 Jun 2005 15:50:41 +0100 Date: Thu, 23 Jun 2005 15:50:41 +0100 From: Steve Roome To: David Sze Message-ID: <20050623145041.GC64879@bibipentium.lonres.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.4.2.1i Cc: performance@freebsd.org Subject: Re: FreeBSD MySQL still WAY slower than Linux 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: Thu, 23 Jun 2005 14:50:29 -0000 Oops, here's what I was supposed to attach to the email with test results in it. Sorry about that, Steve Roome ######################################################################## /etc/make.conf ######################################################################## WITHOUT_X11=yes WITHOUT_NLS=yes CFLAGS?=-O3 -pipe CPUTYPE?=p4 KERNCONF?=PE2650_i386_steve NO_PROFILE=true MASTER_SITE_BACKUP?= ftp://ftp.uk.freebsd.org/pub/FreeBSD/ports/distfiles/${DIST_SUBDIR}/ MASTER_SITE_OVERRIDE?= ${MASTER_SITE_BACKUP} SUP_UPDATE=yes SUP=/usr/local/bin/cvsup SUPFLAGS=-g -L 2 SUPHOST=cvsup.uk.FreeBSD.org SUPFILE=/usr/src/supfile PORTSSUPFILE=/usr/ports/ports-supfile # added by use.perl 2005-06-23 10:21:11 PERL_VER=5.8.6 PERL_VERSION=5.8.6 ######################################################################## # Kernel configuration ######################################################################## # $FreeBSD: src/sys/i386/conf/GENERIC,v 1.413.2.8 2004/10/24 17:42:08 scottl Exp $ machine i386 cpu I686_CPU ident PE2650_i386_1 options MAXDSIZ=(2048UL*1024*1024) options SCHED_4BSD # 4BSD scheduler options INET # InterNETworking options FFS # Berkeley Fast Filesystem options SOFTUPDATES # Enable FFS soft updates support options UFS_ACL # Support for access control lists options UFS_DIRHASH # Improve performance on big directories # can be dynamically loaded: options NFSCLIENT # Network Filesystem Client # can be dynamically loaded: options NFSSERVER # Network Filesystem Server # can be dynamically loaded: options MSDOSFS # MSDOS Filesystem # can be dynamically loaded: options CD9660 # ISO 9660 Filesystem # can be dynamically loaded: options PROCFS # Process filesystem (requires PSEUDOFS) options PSEUDOFS # Pseudo-filesystem framework options GEOM_GPT # GUID Partition Tables. options COMPAT_43 # Compatible with BSD 4.3 [KEEP THIS!] options COMPAT_FREEBSD4 # Compatible with FreeBSD4 options SCSI_DELAY=1000 # Delay (in ms) before probing SCSI options KTRACE # ktrace(1) support options SYSVSHM # SYSV-style shared memory options SYSVMSG # SYSV-style message queues options SYSVSEM # SYSV-style semaphores options _KPOSIX_PRIORITY_SCHEDULING # POSIX P1003_1B real-time extensions options KBD_INSTALL_CDEV # install a CDEV entry in /dev options ADAPTIVE_GIANT # Giant mutex is adaptive. options SMP device apic # I/O APIC device isa device pci device fdc device ata device atapicd # ATAPI CDROM drives options ATA_STATIC_ID # Static device numbering device scbus # SCSI bus (required for SCSI) # can be dynamically loaded: device ch # SCSI media changers device da # Direct Access (disks) # can be dynamically loaded: device sa # Sequential Access (tape etc) device pass # Passthrough device (direct SCSI access) # can be dynamically loaded: device ses # SCSI Environmental Services (and SAF-TE) device aac # Adaptec FSA RAID device aacp # SCSI passthrough for aac (requires CAM) device atkbdc # AT keyboard controller device atkbd # AT keyboard device vga # VGA video card driver device sc # can be dynamically loaded: device agp # support several AGP chipsets device npx device sio # 8250, 16[45]50 based serial ports device miibus # MII bus support device bge # Broadcom BCM570xx Gigabit Ethernet device loop # Network loopback device mem # Memory and kernel memory devices device io # I/O device device random # Entropy device device ether # Ethernet support # can be dynamically loaded: device ppp # Kernel PPP # can be dynamically loaded: device tun # Packet tunnel. device pty # Pseudo-ttys (telnet etc) device md # Memory "disks" device gif # IPv6 and IPv4 tunneling device bpf # Berkeley packet filter device amr device em ######################################################################## # dmesg output ######################################################################## Copyright (c) 1992-2005 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 6.0-CURRENT #2: Wed Jun 22 17:30:47 BST 2005 root@unoctbium.lonres.com:/usr/obj/usr/src/sys/PE2650_i386_steve ACPI APIC Table: Timecounter "i8254" frequency 1193182 Hz quality 0 CPU: Intel(R) Xeon(TM) CPU 2.80GHz (2793.01-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0xf34 Stepping = 4 Features=0xbfebfbff Features2=0x441d> real memory = 3489398784 (3327 MB) avail memory = 3419168768 (3260 MB) FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs cpu0 (BSP): APIC ID: 0 cpu1 (AP): APIC ID: 6 ioapic0: Changing APIC ID to 7 ioapic1: Changing APIC ID to 8 ioapic1: WARNING: intbase 32 != expected base 24 ioapic2: Changing APIC ID to 9 ioapic2: WARNING: intbase 64 != expected base 56 ioapic3: Changing APIC ID to 10 ioapic3: WARNING: intbase 96 != expected base 88 ioapic0 irqs 0-23 on motherboard ioapic1 irqs 32-55 on motherboard ioapic2 irqs 64-87 on motherboard ioapic3 irqs 96-119 on motherboard npx0: [FAST] npx0: on motherboard npx0: INT 16 interface acpi0: on motherboard acpi0: Power Button (fixed) pci_link0: irq 7 on acpi0 pci_link1: irq 5 on acpi0 pci_link2: irq 10 on acpi0 pci_link3: on acpi0 pci_link4: on acpi0 pci_link5: on acpi0 pci_link6: on acpi0 pci_link7: on acpi0 Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 acpi_timer0: <24-bit timer at 3.579545MHz> port 0x808-0x80b on acpi0 cpu0: on acpi0 cpu1: on acpi0 pcib0: port 0xcf8-0xcff on acpi0 pci0: on pcib0 pcib1: at device 2.0 on pci0 pci1: on pcib1 pcib2: at device 0.0 on pci1 pci2: on pcib2 amr0: mem 0xd80f0000-0xd80fffff,0xdfec0000-0xdfefffff irq 46 at device 14.0 on pci2 amr0: Firmware 513O, BIOS H418, 256MB RAM pcib3: at device 0.2 on pci1 pci3: on pcib3 pcib4: at device 4.0 on pci0 pci4: on pcib4 pcib5: at device 5.0 on pci0 pci5: on pcib5 pcib6: at device 0.0 on pci5 pci6: on pcib6 em0: port 0xecc0-0xecff mem 0xdfbe0000-0xdfbfffff irq 64 at device 7.0 on pci6 em0: Ethernet address: 00:11:43:33:9c:e3 em0: Speed:N/A Duplex:N/A pcib7: at device 0.2 on pci5 pci7: on pcib7 em1: port 0xdcc0-0xdcff mem 0xdf9e0000-0xdf9fffff irq 65 at device 8.0 on pci7 em1: Ethernet address: 00:11:43:33:9c:e4 em1: Speed:N/A Duplex:N/A pcib8: at device 6.0 on pci0 pci8: on pcib8 pcib9: at device 0.0 on pci8 pci9: on pcib9 pcib10: at device 0.2 on pci8 pci10: on pcib10 pcib11: at device 30.0 on pci0 pci11: on pcib11 pci11: at device 13.0 (no driver attached) isab0: at device 31.0 on pci0 isa0: on isab0 atapci0: port 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0xfc00-0xfc0f at device 31.1 on pci0 ata0: on atapci0 ata1: on atapci0 fdc0: port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on acpi0 fdc0: [FAST] fd0: <1440-KB 3.5" drive> on fdc0 drive 0 atkbdc0: port 0x60,0x64 irq 1 on acpi0 atkbd0: irq 1 on atkbdc0 kbd0 at atkbd0 atkbd0: [GIANT-LOCKED] sio0: <16550A-compatible COM port> port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 sio0: type 16550A orm0: at iomem 0xc0000-0xcafff,0xec000-0xeffff on isa0 sc0: at flags 0x100 on isa0 sc0: VGA <16 virtual consoles, flags=0x300> vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 sio1: configured irq 3 not in bitmap of probed irqs 0 sio1: port may not be enabled Timecounters tick every 1.000 msec acd0: CDROM at ata0-master UDMA33 pass0 at amr0 bus 0 target 6 lun 0 pass0: Fixed Processor SCSI-2 device amrd0: on amr0 amrd0: 69360MB (142049280 sectors) RAID 5 (optimal) amrd1: on amr0 amrd1: 69360MB (142049280 sectors) RAID 5 (optimal) SMP: AP CPU #1 Launched! Trying to mount root from ufs:/dev/amrd0s1a em0: link state changed to UP From owner-freebsd-performance@FreeBSD.ORG Thu Jun 23 17:26:26 2005 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 B6B7116A424 for ; Thu, 23 Jun 2005 17:26:26 +0000 (GMT) (envelope-from mike@sentex.net) Received: from smarthost1.sentex.ca (smarthost1.sentex.ca [64.7.153.18]) by mx1.FreeBSD.org (Postfix) with ESMTP id 71E2043D4C for ; Thu, 23 Jun 2005 17:26:26 +0000 (GMT) (envelope-from mike@sentex.net) Received: from pumice3.sentex.ca (pumice3.sentex.ca [64.7.153.26]) by smarthost1.sentex.ca (8.13.3/8.13.3) with ESMTP id j5NHPsm3029799 for ; Thu, 23 Jun 2005 13:25:55 -0400 (EDT) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by pumice3.sentex.ca (8.13.3/8.13.3) with ESMTP id j5NHQO50028143 for ; Thu, 23 Jun 2005 13:26:24 -0400 (EDT) (envelope-from mike@sentex.net) Received: from simian.sentex.net (simeon.sentex.ca [192.168.43.27]) by lava.sentex.ca (8.13.3/8.13.3) with ESMTP id j5NHQN6L010210 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Thu, 23 Jun 2005 13:26:23 -0400 (EDT) (envelope-from mike@sentex.net) Message-Id: <6.2.1.2.0.20050623131942.039d4658@64.7.153.2> X-Mailer: QUALCOMM Windows Eudora Version 6.2.1.2 Date: Thu, 23 Jun 2005 13:27:35 -0400 To: freebsd-performance@FreeBSD.ORG From: Mike Tancsa Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by amavisd-new X-Scanned-By: MIMEDefang 2.51 on 64.7.153.18 X-Scanned-By: MIMEDefang 2.51 on 64.7.153.26 Cc: Subject: RELENG_4 vs RELENG_5 for mail router 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: Thu, 23 Jun 2005 17:26:27 -0000 We upgraded one of our inbound mail servers from RELENG_4 to RELENG_5. Hardware is the same. Its possible there is a measurement / reporting issue, not sure http://www.tancsa.com/upgrade.html But on the box, it does "feel" faster even at what used to be peak times in terms of responsiveness-- especially how it now handles big blast of spam. So it sort of backups up the numbers from that standpoint. Neither box was overly optimized. Apart from pulling some unused drivers out of the kernel configs, they were both essentially running GENERIC ---Mike -------------------------------------------------------------------- Mike Tancsa, tel +1 519 651 3400 Sentex Communications, mike@sentex.net Providing Internet since 1994 www.sentex.net Cambridge, Ontario Canada www.sentex.net/mike From owner-freebsd-performance@FreeBSD.ORG Thu Jun 23 20:35:48 2005 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 4F06616A41C for ; Thu, 23 Jun 2005 20:35:48 +0000 (GMT) (envelope-from sten@blinkenlights.nl) Received: from ford.blinkenlights.nl (ford.blinkenlights.nl [213.204.211.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 08FD843D53 for ; Thu, 23 Jun 2005 20:35:48 +0000 (GMT) (envelope-from sten@blinkenlights.nl) Received: from tea.blinkenlights.nl (tea.blinkenlights.nl [192.168.1.21]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by ford.blinkenlights.nl (Postfix) with ESMTP id E0F8D3F294; Thu, 23 Jun 2005 22:35:46 +0200 (CEST) Received: by tea.blinkenlights.nl (Postfix, from userid 101) id 7A4DA27C; Thu, 23 Jun 2005 22:35:46 +0200 (CEST) Received: from localhost (localhost [127.0.0.1]) by tea.blinkenlights.nl (Postfix) with ESMTP id 6F5BF42; Thu, 23 Jun 2005 22:35:46 +0200 (CEST) Date: Thu, 23 Jun 2005 22:35:46 +0200 (CEST) From: Sten Spans To: Steven Hartland In-Reply-To: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> Message-ID: References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-performance@freebsd.org Subject: Re: Fibre Gig card recommendations? 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: Thu, 23 Jun 2005 20:35:48 -0000 On Thu, 23 Jun 2005, Steven Hartland wrote: > Can anyone give me a Fibre Gig card recommendations PCI-X > based that they have used in FreeBSD 5.4 machines preferably? Intel pro/1000 cards using the em(4) driver are most common, these would be the safest bet. There might be better choices out there, but these wouldn't have the amount of testing the intel driver gets. man -k gigabit provides a reasonable list of drivers btw. -- Sten Spans "There is a crack in everything, that's how the light gets in." Leonard Cohen - Anthem From owner-freebsd-performance@FreeBSD.ORG Thu Jun 23 22:40:21 2005 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 3123F16A427 for ; Thu, 23 Jun 2005 22:40:21 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (www1.multiplay.co.uk [212.42.16.7]) by mx1.FreeBSD.org (Postfix) with ESMTP id BB60E43D5C for ; Thu, 23 Jun 2005 22:40:20 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([217.41.249.254]) by multiplay.co.uk (multiplay.co.uk [212.42.16.7]) (MDaemon.PRO.v8.0.2.R) with ESMTP id md50001551548.msg for ; Thu, 23 Jun 2005 23:35:05 +0100 Message-ID: <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> From: "Steven Hartland" To: "Sten Spans" References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> Date: Thu, 23 Jun 2005 23:40:02 +0100 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 6.00.2900.2527 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 X-Spam-Processed: multiplay.co.uk, Thu, 23 Jun 2005 23:35:05 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 217.41.249.254 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Thu, 23 Jun 2005 23:35:06 +0100 Cc: freebsd-performance@freebsd.org Subject: Re: Fibre Gig card recommendations? 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: Thu, 23 Jun 2005 22:40:22 -0000 Yer know about the list but was looking for real usage experiences as I've tried supported cards before e.g. netgear and it just panics the machine with just ping :( Steve / K ----- Original Message ----- From: "Sten Spans" > On Thu, 23 Jun 2005, Steven Hartland wrote: > >> Can anyone give me a Fibre Gig card recommendations PCI-X >> based that they have used in FreeBSD 5.4 machines preferably? > > Intel pro/1000 cards using the em(4) driver are most common, > these would be the safest bet. There might be better choices > out there, but these wouldn't have the amount of testing the > intel driver gets. > > man -k gigabit > > provides a reasonable list of drivers btw. > > -- > Sten Spans > > "There is a crack in everything, that's how the light gets in." > Leonard Cohen - Anthem > > ================================================ 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 (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Fri Jun 24 00:10:49 2005 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 6360716A41C for ; Fri, 24 Jun 2005 00:10:49 +0000 (GMT) (envelope-from sten@blinkenlights.nl) Received: from ford.blinkenlights.nl (ford.blinkenlights.nl [213.204.211.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0FEFC43D48 for ; Fri, 24 Jun 2005 00:10:48 +0000 (GMT) (envelope-from sten@blinkenlights.nl) Received: from tea.blinkenlights.nl (tea.blinkenlights.nl [IPv6:2001:960:301:3:a00:20ff:fe85:fa39]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by ford.blinkenlights.nl (Postfix) with ESMTP id 17E0C3F294; Fri, 24 Jun 2005 02:10:47 +0200 (CEST) Received: by tea.blinkenlights.nl (Postfix, from userid 101) id A4C7827C; Fri, 24 Jun 2005 02:10:46 +0200 (CEST) Received: from localhost (localhost [127.0.0.1]) by tea.blinkenlights.nl (Postfix) with ESMTP id 8B0E742; Fri, 24 Jun 2005 02:10:46 +0200 (CEST) Date: Fri, 24 Jun 2005 02:10:46 +0200 (CEST) From: Sten Spans To: Steven Hartland In-Reply-To: <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> Message-ID: References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-performance@freebsd.org Subject: Re: Fibre Gig card recommendations? 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, 24 Jun 2005 00:10:49 -0000 On Thu, 23 Jun 2005, Steven Hartland wrote: > Yer know about the list but was looking for real usage experiences > as I've tried supported cards before e.g. netgear and it just panics the > machine with just ping :( Get an Intal gigabit card. That's my advice. -- Sten Spans "There is a crack in everything, that's how the light gets in." Leonard Cohen - Anthem From owner-freebsd-performance@FreeBSD.ORG Fri Jun 24 11:29:04 2005 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 E056716A41C for ; Fri, 24 Jun 2005 11:29:04 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from mh1.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id A411E43D49 for ; Fri, 24 Jun 2005 11:29:04 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [10.177.171.220] (neutrino.centtech.com [10.177.171.220]) by mh1.centtech.com (8.13.1/8.13.1) with ESMTP id j5OBSrix015711; Fri, 24 Jun 2005 06:28:57 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <42BBEE70.1050503@centtech.com> Date: Fri, 24 Jun 2005 06:28:48 -0500 From: Eric Anderson User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.8) Gecko/20050603 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Steven Hartland References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> In-Reply-To: <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.82/955/Thu Jun 23 16:08:42 2005 on mh1.centtech.com X-Virus-Status: Clean Cc: Sten Spans , freebsd-performance@freebsd.org Subject: Re: Fibre Gig card recommendations? 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, 24 Jun 2005 11:29:05 -0000 Steven Hartland wrote: > Yer know about the list but was looking for real usage experiences > as I've tried supported cards before e.g. netgear and it just panics the > machine with just ping :( I use the em cards (Intel Pro 1000/MT's and the like) in many machines here, and they are rock solid. You'll pay a little more for them, but there is a reason for it. Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology A lost ounce of gold may be found, a lost moment of time never. ------------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Fri Jun 24 11:37:48 2005 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 D3B3116A41C for ; Fri, 24 Jun 2005 11:37:48 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (www1.multiplay.co.uk [212.42.16.7]) by mx1.FreeBSD.org (Postfix) with ESMTP id 602B843D48 for ; Fri, 24 Jun 2005 11:37:48 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([217.41.249.254]) by multiplay.co.uk (multiplay.co.uk [212.42.16.7]) (MDaemon.PRO.v8.0.2.R) with ESMTP id md50001552787.msg for ; Fri, 24 Jun 2005 12:32:19 +0100 Message-ID: <018001c578b1$156a26f0$fef929d9@multiplay.co.uk> From: "Steven Hartland" To: "Eric Anderson" References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> <42BBEE70.1050503@centtech.com> Date: Fri, 24 Jun 2005 12:37:16 +0100 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 6.00.2900.2527 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 X-Spam-Processed: multiplay.co.uk, Fri, 24 Jun 2005 12:32:19 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 217.41.249.254 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Fri, 24 Jun 2005 12:32:19 +0100 Cc: Sten Spans , freebsd-performance@freebsd.org Subject: Re: Fibre Gig card recommendations? 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, 24 Jun 2005 11:37:48 -0000 Thanks for that. Steve / K ----- Original Message ----- From: "Eric Anderson" > > I use the em cards (Intel Pro 1000/MT's and the like) in many machines > here, and they are rock solid. You'll pay a little more for them, but > there is a reason for it. ================================================ 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 (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Fri Jun 24 21:40:16 2005 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 300BA16A420 for ; Fri, 24 Jun 2005 21:40:16 +0000 (GMT) (envelope-from arkadi@mebius.lv) Received: from mail.hosting.lv (mail.hosting.lv [62.85.37.83]) by mx1.FreeBSD.org (Postfix) with ESMTP id DB27B43D5D for ; Fri, 24 Jun 2005 21:40:14 +0000 (GMT) (envelope-from arkadi@mebius.lv) Received: from lithium.bad.lv ([62.85.6.146]) by mail.hosting.lv with smtp (TLSv1:AES256-SHA:256) id 1Dlvth-000Iqc-6v; Sat, 25 Jun 2005 00:39:40 +0300 Received: by lithium.bad.lv (sSMTP sendmail emulation); Sat, 25 Jun 2005 00:39:26 +0300 From: "Arkadi Shishlov" Date: Sat, 25 Jun 2005 00:39:26 +0300 To: freebsd-performance@freebsd.org Message-ID: <20050624213926.GA7825@mebius.lv> References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> <42BBEE70.1050503@centtech.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <42BBEE70.1050503@centtech.com> User-Agent: Mutt/1.5.8i X-Spam-Score: -2.8 (--) Subject: Re: Fibre Gig card recommendations? 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, 24 Jun 2005 21:40:17 -0000 On Fri, Jun 24, 2005 at 06:28:48AM -0500, Eric Anderson wrote: > Steven Hartland wrote: > >Yer know about the list but was looking for real usage experiences > >as I've tried supported cards before e.g. netgear and it just panics the > >machine with just ping :( > > I use the em cards (Intel Pro 1000/MT's and the like) in many machines > here, and they are rock solid. You'll pay a little more for them, but > there is a reason for it. Whats about performance and stability with MTU > 1500? I tried increasing MTU on my Intel-made servers to speed-up NFS, but both 5.3 em and 2.x Intel provided drivers get stuck after some time with interface in OACTIVE state. arkadi. From owner-freebsd-performance@FreeBSD.ORG Sat Jun 25 03:45:10 2005 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 8828216A41C for ; Sat, 25 Jun 2005 03:45:10 +0000 (GMT) (envelope-from tom.hurst@clara.net) Received: from spork.qfe3.net (spork.qfe3.net [212.13.207.101]) by mx1.FreeBSD.org (Postfix) with ESMTP id 611B943D58 for ; Sat, 25 Jun 2005 03:45:09 +0000 (GMT) (envelope-from tom.hurst@clara.net) Received: from [81.104.55.176] (helo=voi.aagh.net) by spork.qfe3.net with esmtp (Exim 4.50) id 1Dm1bP-0001Us-FD; Sat, 25 Jun 2005 04:45:07 +0100 Received: from freaky by voi.aagh.net with local (Exim 4.51 (FreeBSD)) id 1Dm1bO-000PM4-ST; Sat, 25 Jun 2005 04:45:06 +0100 Date: Sat, 25 Jun 2005 04:45:06 +0100 From: Thomas Hurst To: Arkadi Shishlov Message-ID: <20050625034506.GA96367@voi.aagh.net> Mail-Followup-To: Arkadi Shishlov , freebsd-performance@freebsd.org References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk> <03bf01c57844$811874a0$fef929d9@multiplay.co.uk> <42BBEE70.1050503@centtech.com> <20050624213926.GA7825@mebius.lv> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20050624213926.GA7825@mebius.lv> Organization: Not much. User-Agent: Mutt/1.5.9i Sender: Thomas Hurst X-RBL-Warning: 81.104.55.176 is in RBL blacklist at dnsbl.sorbs.net Cc: freebsd-performance@freebsd.org Subject: Re: Fibre Gig card recommendations? 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, 25 Jun 2005 03:45:10 -0000 * Arkadi Shishlov (arkadi@mebius.lv) wrote: > > I use the em cards (Intel Pro 1000/MT's and the like) in many > > machines here, and they are rock solid. You'll pay a little more > > for them, but there is a reason for it. > > Whats about performance and stability with MTU > 1500? I tried > increasing MTU on my Intel-made servers to speed-up NFS, but both > 5.3 em and 2.x Intel provided drivers get stuck after some time with > interface in OACTIVE state. I've been using MTU=9014 for a while now without problems, aside from the odd glitch with autonegotiation. Switch is an SMC 8505T, using both WinXP and FreeBSD 5 drivers. -- Thomas 'Freaky' Hurst http://hur.st/ From owner-freebsd-performance@FreeBSD.ORG Sat Jun 25 07:11:22 2005 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 B293C16A41C for ; Sat, 25 Jun 2005 07:11:22 +0000 (GMT) (envelope-from ap@bnc.net) Received: from mailomat.net (f-1.mailomat.net [217.110.117.101]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4976E43D4C for ; Sat, 25 Jun 2005 07:11:21 +0000 (GMT) (envelope-from ap@bnc.net) X-Mailomat-SpamCatcher-Score: 2 [X] Received: from [212.202.16.13] (account ap@bnc.net HELO bug) by mailomat.net (CommuniGate Pro SMTP 4.2) with ESMTP-TLS id 4816077; Sat, 25 Jun 2005 09:11:18 +0200 Message-ID: <00ff01c57955$0e5771c0$7000a8c0@bug> From: "Achim Patzner" To: "Arkadi Shishlov" , References: <000f01c577dd$0b82dad0$fef929d9@multiplay.co.uk><03bf01c57844$811874a0$fef929d9@multiplay.co.uk><42BBEE70.1050503@centtech.com> <20050624213926.GA7825@mebius.lv> Date: Sat, 25 Jun 2005 09:10:51 +0200 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 6.00.2900.2180 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2180 Cc: Subject: Re: Fibre Gig card recommendations? 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, 25 Jun 2005 07:11:22 -0000 From: "Arkadi Shishlov" > Whats about performance and stability with MTU > 1500? I tried increasing > MTU on my Intel-made servers to speed-up NFS, but both 5.3 em and 2.x > Intel > provided drivers get stuck after some time with interface in OACTIVE > state. The same happened to us too, but I tracked it down to certain built-in NICs on Mainboards. I had good success with NatSemi NICs, too. Especially at even larger MTUs. Achim From owner-freebsd-performance@FreeBSD.ORG Sat Jun 25 14:06:57 2005 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 4F1EC16A41C for ; Sat, 25 Jun 2005 14:06:57 +0000 (GMT) (envelope-from mv@roq.com) Received: from p4.roq.com (ns1.ecoms.com [207.44.130.137]) by mx1.FreeBSD.org (Postfix) with ESMTP id 19BB643D49 for ; Sat, 25 Jun 2005 14:06:54 +0000 (GMT) (envelope-from mv@roq.com) Received: from p4.roq.com (localhost.roq.com [127.0.0.1]) by p4.roq.com (Postfix) with ESMTP id 0F3574D9C1; Sat, 25 Jun 2005 14:07:13 +0000 (GMT) Received: from [10.0.1.8] (adsl-143-85.swiftdsl.com.au [218.214.143.85]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by p4.roq.com (Postfix) with ESMTP id A2C254D98D; Sat, 25 Jun 2005 14:07:10 +0000 (GMT) Message-ID: <42BD64F1.4080001@roq.com> Date: Sun, 26 Jun 2005 00:06:41 +1000 From: Michael Vince User-Agent: Mozilla Thunderbird 1.0.2 (Windows/20050317) X-Accept-Language: en-us, en MIME-Version: 1.0 To: Steve Roome References: <20050623145041.GC64879@bibipentium.lonres.com> In-Reply-To: <20050623145041.GC64879@bibipentium.lonres.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV using ClamSMTP Cc: performance@freebsd.org Subject: Re: FreeBSD MySQL still WAY slower than Linux 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, 25 Jun 2005 14:06:57 -0000 Your posting a lot of configuration here except the most easily important one for performance in MySQL, thats your my.cnf configuration file You will more then double your performance if you just start off by copying /usr/local/share/mysql/my-large.cnf to /var/db/mysql MySQL out of the box setup to use a tiny amount of ram and it wouldn't surprise me if a lot of Linux distributions have a much more high performance my.cnf file since most distributions are aimed at people who don't know what they are doing. Steve Roome wrote: >Oops, here's what I was supposed to attach to the email with test results in it. > >Sorry about that, > > Steve Roome > >######################################################################## >/etc/make.conf >######################################################################## > >WITHOUT_X11=yes >WITHOUT_NLS=yes > >CFLAGS?=-O3 -pipe >CPUTYPE?=p4 >KERNCONF?=PE2650_i386_steve >NO_PROFILE=true > >MASTER_SITE_BACKUP?= ftp://ftp.uk.freebsd.org/pub/FreeBSD/ports/distfiles/${DIST_SUBDIR}/ >MASTER_SITE_OVERRIDE?= ${MASTER_SITE_BACKUP} > >SUP_UPDATE=yes >SUP=/usr/local/bin/cvsup >SUPFLAGS=-g -L 2 >SUPHOST=cvsup.uk.FreeBSD.org >SUPFILE=/usr/src/supfile >PORTSSUPFILE=/usr/ports/ports-supfile ># added by use.perl 2005-06-23 10:21:11 >PERL_VER=5.8.6 >PERL_VERSION=5.8.6 > > >######################################################################## ># Kernel configuration >######################################################################## ># $FreeBSD: src/sys/i386/conf/GENERIC,v 1.413.2.8 2004/10/24 17:42:08 scottl Exp $ > >machine i386 >cpu I686_CPU >ident PE2650_i386_1 > >options MAXDSIZ=(2048UL*1024*1024) > >options SCHED_4BSD # 4BSD scheduler >options INET # InterNETworking >options FFS # Berkeley Fast Filesystem >options SOFTUPDATES # Enable FFS soft updates support >options UFS_ACL # Support for access control lists >options UFS_DIRHASH # Improve performance on big directories ># can be dynamically loaded: options NFSCLIENT # Network Filesystem Client ># can be dynamically loaded: options NFSSERVER # Network Filesystem Server ># can be dynamically loaded: options MSDOSFS # MSDOS Filesystem ># can be dynamically loaded: options CD9660 # ISO 9660 Filesystem ># can be dynamically loaded: options PROCFS # Process filesystem (requires PSEUDOFS) >options PSEUDOFS # Pseudo-filesystem framework >options GEOM_GPT # GUID Partition Tables. >options COMPAT_43 # Compatible with BSD 4.3 [KEEP THIS!] >options COMPAT_FREEBSD4 # Compatible with FreeBSD4 >options SCSI_DELAY=1000 # Delay (in ms) before probing SCSI >options KTRACE # ktrace(1) support >options SYSVSHM # SYSV-style shared memory >options SYSVMSG # SYSV-style message queues >options SYSVSEM # SYSV-style semaphores >options _KPOSIX_PRIORITY_SCHEDULING # POSIX P1003_1B real-time extensions >options KBD_INSTALL_CDEV # install a CDEV entry in /dev >options ADAPTIVE_GIANT # Giant mutex is adaptive. > >options SMP >device apic # I/O APIC > >device isa >device pci > >device fdc > >device ata >device atapicd # ATAPI CDROM drives >options ATA_STATIC_ID # Static device numbering > >device scbus # SCSI bus (required for SCSI) ># can be dynamically loaded: device ch # SCSI media changers >device da # Direct Access (disks) ># can be dynamically loaded: device sa # Sequential Access (tape etc) >device pass # Passthrough device (direct SCSI access) ># can be dynamically loaded: device ses # SCSI Environmental Services (and SAF-TE) > >device aac # Adaptec FSA RAID >device aacp # SCSI passthrough for aac (requires CAM) > >device atkbdc # AT keyboard controller >device atkbd # AT keyboard > >device vga # VGA video card driver >device sc ># can be dynamically loaded: device agp # support several AGP chipsets >device npx >device sio # 8250, 16[45]50 based serial ports > >device miibus # MII bus support >device bge # Broadcom BCM570xx Gigabit Ethernet > >device loop # Network loopback >device mem # Memory and kernel memory devices >device io # I/O device >device random # Entropy device >device ether # Ethernet support ># can be dynamically loaded: device ppp # Kernel PPP ># can be dynamically loaded: device tun # Packet tunnel. >device pty # Pseudo-ttys (telnet etc) >device md # Memory "disks" >device gif # IPv6 and IPv4 tunneling >device bpf # Berkeley packet filter >device amr >device em > > >######################################################################## ># dmesg output >######################################################################## > > >Copyright (c) 1992-2005 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 6.0-CURRENT #2: Wed Jun 22 17:30:47 BST 2005 > root@unoctbium.lonres.com:/usr/obj/usr/src/sys/PE2650_i386_steve >ACPI APIC Table: >Timecounter "i8254" frequency 1193182 Hz quality 0 >CPU: Intel(R) Xeon(TM) CPU 2.80GHz (2793.01-MHz 686-class CPU) > Origin = "GenuineIntel" Id = 0xf34 Stepping = 4 > Features=0xbfebfbff > Features2=0x441d> >real memory = 3489398784 (3327 MB) >avail memory = 3419168768 (3260 MB) >FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs > cpu0 (BSP): APIC ID: 0 > cpu1 (AP): APIC ID: 6 >ioapic0: Changing APIC ID to 7 >ioapic1: Changing APIC ID to 8 >ioapic1: WARNING: intbase 32 != expected base 24 >ioapic2: Changing APIC ID to 9 >ioapic2: WARNING: intbase 64 != expected base 56 >ioapic3: Changing APIC ID to 10 >ioapic3: WARNING: intbase 96 != expected base 88 >ioapic0 irqs 0-23 on motherboard >ioapic1 irqs 32-55 on motherboard >ioapic2 irqs 64-87 on motherboard >ioapic3 irqs 96-119 on motherboard >npx0: [FAST] >npx0: on motherboard >npx0: INT 16 interface >acpi0: on motherboard >acpi0: Power Button (fixed) >pci_link0: irq 7 on acpi0 >pci_link1: irq 5 on acpi0 >pci_link2: irq 10 on acpi0 >pci_link3: on acpi0 >pci_link4: on acpi0 >pci_link5: on acpi0 >pci_link6: on acpi0 >pci_link7: on acpi0 >Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 >acpi_timer0: <24-bit timer at 3.579545MHz> port 0x808-0x80b on acpi0 >cpu0: on acpi0 >cpu1: on acpi0 >pcib0: port 0xcf8-0xcff on acpi0 >pci0: on pcib0 >pcib1: at device 2.0 on pci0 >pci1: on pcib1 >pcib2: at device 0.0 on pci1 >pci2: on pcib2 >amr0: mem 0xd80f0000-0xd80fffff,0xdfec0000-0xdfefffff irq 46 at device 14.0 on pci2 >amr0: Firmware 513O, BIOS H418, 256MB RAM >pcib3: at device 0.2 on pci1 >pci3: on pcib3 >pcib4: at device 4.0 on pci0 >pci4: on pcib4 >pcib5: at device 5.0 on pci0 >pci5: on pcib5 >pcib6: at device 0.0 on pci5 >pci6: on pcib6 >em0: port 0xecc0-0xecff mem 0xdfbe0000-0xdfbfffff irq 64 at device 7.0 on pci6 >em0: Ethernet address: 00:11:43:33:9c:e3 >em0: Speed:N/A Duplex:N/A >pcib7: at device 0.2 on pci5 >pci7: on pcib7 >em1: port 0xdcc0-0xdcff mem 0xdf9e0000-0xdf9fffff irq 65 at device 8.0 on pci7 >em1: Ethernet address: 00:11:43:33:9c:e4 >em1: Speed:N/A Duplex:N/A >pcib8: at device 6.0 on pci0 >pci8: on pcib8 >pcib9: at device 0.0 on pci8 >pci9: on pcib9 >pcib10: at device 0.2 on pci8 >pci10: on pcib10 >pcib11: at device 30.0 on pci0 >pci11: on pcib11 >pci11: at device 13.0 (no driver attached) >isab0: at device 31.0 on pci0 >isa0: on isab0 >atapci0: port 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0xfc00-0xfc0f at device 31.1 on pci0 >ata0: on atapci0 >ata1: on atapci0 >fdc0: port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on acpi0 >fdc0: [FAST] >fd0: <1440-KB 3.5" drive> on fdc0 drive 0 >atkbdc0: port 0x60,0x64 irq 1 on acpi0 >atkbd0: irq 1 on atkbdc0 >kbd0 at atkbd0 >atkbd0: [GIANT-LOCKED] >sio0: <16550A-compatible COM port> port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 >sio0: type 16550A >orm0: at iomem 0xc0000-0xcafff,0xec000-0xeffff on isa0 >sc0: at flags 0x100 on isa0 >sc0: VGA <16 virtual consoles, flags=0x300> >vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 >sio1: configured irq 3 not in bitmap of probed irqs 0 >sio1: port may not be enabled >Timecounters tick every 1.000 msec >acd0: CDROM at ata0-master UDMA33 >pass0 at amr0 bus 0 target 6 lun 0 >pass0: Fixed Processor SCSI-2 device >amrd0: on amr0 >amrd0: 69360MB (142049280 sectors) RAID 5 (optimal) >amrd1: on amr0 >amrd1: 69360MB (142049280 sectors) RAID 5 (optimal) >SMP: AP CPU #1 Launched! >Trying to mount root from ufs:/dev/amrd0s1a >em0: link state changed to UP >_______________________________________________ >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 Jun 25 17:26:31 2005 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 D8BC916A41C for ; Sat, 25 Jun 2005 17:26:31 +0000 (GMT) (envelope-from shawnm@iodamedia.net) Received: from kcmop04.iodamedia.net (kcmop04.iodamedia.net [66.39.199.5]) by mx1.FreeBSD.org (Postfix) with ESMTP id 41D3543D53 for ; Sat, 25 Jun 2005 17:26:31 +0000 (GMT) (envelope-from shawnm@iodamedia.net) Received: from localhost (localhost.iodamedia.net [127.0.0.1]) by kcmop04.iodamedia.net (Postfix) with ESMTP id 9BD26204F46; Sat, 25 Jun 2005 12:26:28 -0500 (CDT) Received: from kcmop04.iodamedia.net ([127.0.0.1]) by localhost (kcmop04.iodamedia.net [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 14287-06; Sat, 25 Jun 2005 12:26:23 -0500 (CDT) Received: from zeus (CPE-65-30-37-142.kc.res.rr.com [65.30.37.142]) by kcmop04.iodamedia.net (Postfix) with ESMTP id 42DAD204E1F; Sat, 25 Jun 2005 12:26:23 -0500 (CDT) From: "Shawn Mitchell" To: "'Michael Vince'" , "'Steve Roome'" Date: Sat, 25 Jun 2005 12:26:22 -0500 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit X-Mailer: Microsoft Office Outlook, Build 11.0.6353 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2527 In-reply-to: <42BD64F1.4080001@roq.com> Thread-Index: AcV5jzI7npYbBzO7QdWJDwdYsulbqQAGmNXQ Message-Id: <20050625172623.42DAD204E1F@kcmop04.iodamedia.net> X-Virus-Scanned: amavisd-new at kcmop04.iodamedia.net Cc: performance@freebsd.org Subject: RE: FreeBSD MySQL still WAY slower than Linux 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, 25 Jun 2005 17:26:32 -0000 I tested a MySQL install on a Dell 6600. It's specs were 8 GB ram, 12 x 73 15k rpm drives (Ultra320) on a RAID5, 4 Xeon MP w/ 2 meg of cache, HT enabled so the OS saw 8 CPU's. Every time, a stock linux install (SuSE, CentOS, and Fedora) were always faster than FreeBSD stock, or custom kernel utilizing different options. I never could fully benchmark it running on Linux; as I never got the server to max out before my benchmarking machine maxed out. If your using 4.x, add these to your config file options MAXDSIZ="(256*1024*1024)" options MAXSSIZ="(256*1024*1024)" options DFLDSIZ="(256*1024*1024)" I noticed a HUGE difference on FreeBSD with those added, but it still doesn't crank up there with Linux. Also, default linux install's do not make it use more ram. You still have to copy one of the my-xxx.cnf files over to /etc/my.cnf or /usr/local/etc/my.cnf MySQL is developed on Linux, and ported to FreeBSD. That's the best explanation you'll get probably. -----Original Message----- From: owner-freebsd-performance@freebsd.org [mailto:owner-freebsd-performance@freebsd.org] On Behalf Of Michael Vince Sent: Saturday, June 25, 2005 9:07 AM To: Steve Roome Cc: performance@freebsd.org Subject: Re: FreeBSD MySQL still WAY slower than Linux Your posting a lot of configuration here except the most easily important one for performance in MySQL, thats your my.cnf configuration file You will more then double your performance if you just start off by copying /usr/local/share/mysql/my-large.cnf to /var/db/mysql MySQL out of the box setup to use a tiny amount of ram and it wouldn't surprise me if a lot of Linux distributions have a much more high performance my.cnf file since most distributions are aimed at people who don't know what they are doing. Steve Roome wrote: >Oops, here's what I was supposed to attach to the email with test results in it. > >Sorry about that, > > Steve Roome > >######################################################################## >/etc/make.conf >######################################################################## > >WITHOUT_X11=yes >WITHOUT_NLS=yes > >CFLAGS?=-O3 -pipe >CPUTYPE?=p4 >KERNCONF?=PE2650_i386_steve >NO_PROFILE=true > >MASTER_SITE_BACKUP?= ftp://ftp.uk.freebsd.org/pub/FreeBSD/ports/distfiles/${DIST_SUBDIR}/ >MASTER_SITE_OVERRIDE?= ${MASTER_SITE_BACKUP} > >SUP_UPDATE=yes >SUP=/usr/local/bin/cvsup >SUPFLAGS=-g -L 2 >SUPHOST=cvsup.uk.FreeBSD.org >SUPFILE=/usr/src/supfile >PORTSSUPFILE=/usr/ports/ports-supfile ># added by use.perl 2005-06-23 10:21:11 >PERL_VER=5.8.6 >PERL_VERSION=5.8.6 > > >######################################################################## ># Kernel configuration >######################################################################## ># $FreeBSD: src/sys/i386/conf/GENERIC,v 1.413.2.8 2004/10/24 17:42:08 scottl Exp $ > >machine i386 >cpu I686_CPU >ident PE2650_i386_1 > >options MAXDSIZ=(2048UL*1024*1024) > >options SCHED_4BSD # 4BSD scheduler >options INET # InterNETworking >options FFS # Berkeley Fast Filesystem >options SOFTUPDATES # Enable FFS soft updates support >options UFS_ACL # Support for access control lists >options UFS_DIRHASH # Improve performance on big directories ># can be dynamically loaded: options NFSCLIENT # Network Filesystem Client ># can be dynamically loaded: options NFSSERVER # Network Filesystem Server ># can be dynamically loaded: options MSDOSFS # MSDOS Filesystem ># can be dynamically loaded: options CD9660 # ISO 9660 Filesystem ># can be dynamically loaded: options PROCFS # Process filesystem (requires PSEUDOFS) >options PSEUDOFS # Pseudo-filesystem framework >options GEOM_GPT # GUID Partition Tables. >options COMPAT_43 # Compatible with BSD 4.3 [KEEP THIS!] >options COMPAT_FREEBSD4 # Compatible with FreeBSD4 >options SCSI_DELAY=1000 # Delay (in ms) before probing SCSI >options KTRACE # ktrace(1) support >options SYSVSHM # SYSV-style shared memory >options SYSVMSG # SYSV-style message queues >options SYSVSEM # SYSV-style semaphores >options _KPOSIX_PRIORITY_SCHEDULING # POSIX P1003_1B real-time extensions >options KBD_INSTALL_CDEV # install a CDEV entry in /dev >options ADAPTIVE_GIANT # Giant mutex is adaptive. > >options SMP >device apic # I/O APIC > >device isa >device pci > >device fdc > >device ata >device atapicd # ATAPI CDROM drives >options ATA_STATIC_ID # Static device numbering > >device scbus # SCSI bus (required for SCSI) ># can be dynamically loaded: device ch # SCSI media changers >device da # Direct Access (disks) ># can be dynamically loaded: device sa # Sequential Access (tape etc) >device pass # Passthrough device (direct SCSI access) ># can be dynamically loaded: device ses # SCSI Environmental Services (and SAF-TE) > >device aac # Adaptec FSA RAID >device aacp # SCSI passthrough for aac (requires CAM) > >device atkbdc # AT keyboard controller >device atkbd # AT keyboard > >device vga # VGA video card driver >device sc ># can be dynamically loaded: device agp # support several AGP chipsets >device npx >device sio # 8250, 16[45]50 based serial ports > >device miibus # MII bus support >device bge # Broadcom BCM570xx Gigabit Ethernet > >device loop # Network loopback >device mem # Memory and kernel memory devices >device io # I/O device >device random # Entropy device >device ether # Ethernet support ># can be dynamically loaded: device ppp # Kernel PPP ># can be dynamically loaded: device tun # Packet tunnel. >device pty # Pseudo-ttys (telnet etc) >device md # Memory "disks" >device gif # IPv6 and IPv4 tunneling >device bpf # Berkeley packet filter >device amr >device em > > >######################################################################## ># dmesg output >######################################################################## > > >Copyright (c) 1992-2005 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 6.0-CURRENT #2: Wed Jun 22 17:30:47 BST 2005 > root@unoctbium.lonres.com:/usr/obj/usr/src/sys/PE2650_i386_steve >ACPI APIC Table: >Timecounter "i8254" frequency 1193182 Hz quality 0 >CPU: Intel(R) Xeon(TM) CPU 2.80GHz (2793.01-MHz 686-class CPU) > Origin = "GenuineIntel" Id = 0xf34 Stepping = 4 > Features=0xbfebfbff > Features2=0x441d> >real memory = 3489398784 (3327 MB) >avail memory = 3419168768 (3260 MB) >FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs > cpu0 (BSP): APIC ID: 0 > cpu1 (AP): APIC ID: 6 >ioapic0: Changing APIC ID to 7 >ioapic1: Changing APIC ID to 8 >ioapic1: WARNING: intbase 32 != expected base 24 >ioapic2: Changing APIC ID to 9 >ioapic2: WARNING: intbase 64 != expected base 56 >ioapic3: Changing APIC ID to 10 >ioapic3: WARNING: intbase 96 != expected base 88 >ioapic0 irqs 0-23 on motherboard >ioapic1 irqs 32-55 on motherboard >ioapic2 irqs 64-87 on motherboard >ioapic3 irqs 96-119 on motherboard >npx0: [FAST] >npx0: on motherboard >npx0: INT 16 interface >acpi0: on motherboard >acpi0: Power Button (fixed) >pci_link0: irq 7 on acpi0 >pci_link1: irq 5 on acpi0 >pci_link2: irq 10 on acpi0 >pci_link3: on acpi0 >pci_link4: on acpi0 >pci_link5: on acpi0 >pci_link6: on acpi0 >pci_link7: on acpi0 >Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000 >acpi_timer0: <24-bit timer at 3.579545MHz> port 0x808-0x80b on acpi0 >cpu0: on acpi0 >cpu1: on acpi0 >pcib0: port 0xcf8-0xcff on acpi0 >pci0: on pcib0 >pcib1: at device 2.0 on pci0 >pci1: on pcib1 >pcib2: at device 0.0 on pci1 >pci2: on pcib2 >amr0: mem 0xd80f0000-0xd80fffff,0xdfec0000-0xdfefffff irq 46 at device 14.0 on pci2 >amr0: Firmware 513O, BIOS H418, 256MB RAM >pcib3: at device 0.2 on pci1 >pci3: on pcib3 >pcib4: at device 4.0 on pci0 >pci4: on pcib4 >pcib5: at device 5.0 on pci0 >pci5: on pcib5 >pcib6: at device 0.0 on pci5 >pci6: on pcib6 >em0: port 0xecc0-0xecff mem 0xdfbe0000-0xdfbfffff irq 64 at device 7.0 on pci6 >em0: Ethernet address: 00:11:43:33:9c:e3 >em0: Speed:N/A Duplex:N/A >pcib7: at device 0.2 on pci5 >pci7: on pcib7 >em1: port 0xdcc0-0xdcff mem 0xdf9e0000-0xdf9fffff irq 65 at device 8.0 on pci7 >em1: Ethernet address: 00:11:43:33:9c:e4 >em1: Speed:N/A Duplex:N/A >pcib8: at device 6.0 on pci0 >pci8: on pcib8 >pcib9: at device 0.0 on pci8 >pci9: on pcib9 >pcib10: at device 0.2 on pci8 >pci10: on pcib10 >pcib11: at device 30.0 on pci0 >pci11: on pcib11 >pci11: at device 13.0 (no driver attached) >isab0: at device 31.0 on pci0 >isa0: on isab0 >atapci0: port 0x1f0-0x1f7,0x3f6,0x170-0x177,0x376,0xfc00-0xfc0f at device 31.1 on pci0 >ata0: on atapci0 >ata1: on atapci0 >fdc0: port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on acpi0 >fdc0: [FAST] >fd0: <1440-KB 3.5" drive> on fdc0 drive 0 >atkbdc0: port 0x60,0x64 irq 1 on acpi0 >atkbd0: irq 1 on atkbdc0 >kbd0 at atkbd0 >atkbd0: [GIANT-LOCKED] >sio0: <16550A-compatible COM port> port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0 >sio0: type 16550A >orm0: at iomem 0xc0000-0xcafff,0xec000-0xeffff on isa0 >sc0: at flags 0x100 on isa0 >sc0: VGA <16 virtual consoles, flags=0x300> >vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 >sio1: configured irq 3 not in bitmap of probed irqs 0 >sio1: port may not be enabled >Timecounters tick every 1.000 msec >acd0: CDROM at ata0-master UDMA33 >pass0 at amr0 bus 0 target 6 lun 0 >pass0: Fixed Processor SCSI-2 device >amrd0: on amr0 >amrd0: 69360MB (142049280 sectors) RAID 5 (optimal) >amrd1: on amr0 >amrd1: 69360MB (142049280 sectors) RAID 5 (optimal) >SMP: AP CPU #1 Launched! >Trying to mount root from ufs:/dev/amrd0s1a >em0: link state changed to UP >_______________________________________________ >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" From owner-freebsd-performance@FreeBSD.ORG Sat Jun 25 20:38:14 2005 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 5BC2516A41C for ; Sat, 25 Jun 2005 20:38:14 +0000 (GMT) (envelope-from danger@rulez.sk) Received: from mail.rulez.sk (DaEmoN.RuLeZ.sK [84.16.32.226]) by mx1.FreeBSD.org (Postfix) with ESMTP id 13F4843D4C for ; Sat, 25 Jun 2005 20:38:14 +0000 (GMT) (envelope-from danger@rulez.sk) Received: from localhost (localhost [127.0.0.1]) by mail.rulez.sk (Postfix) with ESMTP id CB9B71CC42; Sat, 25 Jun 2005 22:38:12 +0200 (CEST) Received: from danger.dnv.dewnet.sk (dewnet [213.215.105.189]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by mail.rulez.sk (Postfix) with ESMTP id 624E71CC41; Sat, 25 Jun 2005 22:38:09 +0200 (CEST) Date: Sat, 25 Jun 2005 21:58:48 +0200 From: Daniel Gerzo X-Mailer: The Bat! (v3.5) UNREG / CD5BF9353B3B7091 X-Priority: 3 (Normal) Message-ID: <1986158848.20050625215848@rulez.sk> To: "Shawn Mitchell" In-Reply-To: <20050625172623.42DAD204E1F@kcmop04.iodamedia.net> References: <42BD64F1.4080001@roq.com> <20050625172623.42DAD204E1F@kcmop04.iodamedia.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at mail.rulez.sk X-Spam-Status: No, hits=-2.934 tagged_above=-999 required=5 tests=[AWL=-0.335, BAYES_00=-2.599] X-Spam-Level: Cc: 'Michael Vince' , 'Steve Roome' , performance@freebsd.org Subject: Re[2]: FreeBSD MySQL still WAY slower than Linux X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Daniel Gerzo List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 25 Jun 2005 20:38:14 -0000 Nemam dobru naladu Shawn, Saturday, June 25, 2005, 7:26:22 PM, si odoslal: > I tested a MySQL install on a Dell 6600. It's specs were 8 GB ram, 12 x 73 > 15k rpm drives (Ultra320) on a RAID5, 4 Xeon MP w/ 2 meg of cache, HT > enabled so the OS saw 8 CPU's. > Every time, a stock linux install (SuSE, CentOS, and Fedora) were always > faster than FreeBSD stock, or custom kernel utilizing different options. > I never could fully benchmark it running on Linux; as I never got the server > to max out before my benchmarking machine maxed out. > If your using 4.x, add these to your config file > options MAXDSIZ="(256*1024*1024)" > options MAXSSIZ="(256*1024*1024)" > options DFLDSIZ="(256*1024*1024)" these are not possible to use under 5.x? > I noticed a HUGE difference on FreeBSD with those added, but it still > doesn't crank up there with Linux. > Also, default linux install's do not make it use more ram. You still have > to copy one of the my-xxx.cnf files over to /etc/my.cnf or > /usr/local/etc/my.cnf > MySQL is developed on Linux, and ported to FreeBSD. That's the best > explanation you'll get probably. > Your posting a lot of configuration here except the most easily > important one for performance in MySQL, thats your my.cnf configuration file > You will more then double your performance if you just start off by copying > /usr/local/share/mysql/my-large.cnf > to > /var/db/mysql > MySQL out of the box setup to use a tiny amount of ram and it wouldn't > surprise me if a lot of Linux distributions have a much more high > performance my.cnf file since most distributions are aimed at people who > don't know what they are doing. -- Nieze by som chcel este nieco napisat, ale uz som to napisal. DanGer, ICQ: 261701668 | e-mail protecting at: http://www.2pu.net/ http://danger.rulez.sk | proxy list at: http://www.proxy-web.com/ | FreeBSD - The Power to Serve! [ s pokrokom by nic nebolo, len nie a nie ho skoncit. ] From owner-freebsd-performance@FreeBSD.ORG Sat Jun 25 22:10:08 2005 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 D5A3216A41C for ; Sat, 25 Jun 2005 22:10:08 +0000 (GMT) (envelope-from tec@mega.net.br) Received: from msrv.matik.com.br (msrv.matik.com.br [200.152.83.14]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2895143D49 for ; Sat, 25 Jun 2005 22:10:07 +0000 (GMT) (envelope-from tec@mega.net.br) Received: from [200.152.82.190] ([200.152.82.190]) by msrv.matik.com.br (8.13.1/8.12.11) with ESMTP id j5PMAAJv081869 for ; Sat, 25 Jun 2005 19:10:10 -0300 (BRST) (envelope-from tec@mega.net.br) From: "T.D.Wipnet (H.M.)" To: freebsd-performance@freebsd.org Date: Sat, 25 Jun 2005 19:09:21 -0300 User-Agent: KMail/1.8 References: <20050623145041.GC64879@bibipentium.lonres.com> <42BD64F1.4080001@roq.com> In-Reply-To: <42BD64F1.4080001@roq.com> Organization: Wipnet Telecom Ltda MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200506251909.24905.tec@mega.net.br> X-Filter-Version: 1.11a (msrv.matik.com.br) X-Virus-Scanned: ClamAV version 0.83, clamav-milter version 0.83 on msrv.matik.com.br X-Virus-Status: Clean Subject: Re: FreeBSD MySQL still WAY slower than Linux X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: tec@mega.net.br List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 25 Jun 2005 22:10:09 -0000 On Saturday 25 June 2005 11:06, Michael Vince wrote: > configuration file You will more then double your performance if > you just start off by copying /usr/local/share/mysql/my-large.cnf you are very fast with your conclusions ... I am not a system engineer but IMO it is not as easy as you say First for answering the thread, IMO, FBSD 4.11 has 20% of performance benefit comparing to 5.x (means 5.2.1-R 5.3-R and 5.4-R) on i386 as P-4 and P-3 machines including AMD This number I'm talking about is for GW-boxes running squid/proxies - [natd] - named - ipfw for certain limitations - dummy - mrtg - apache only for acessing local stats means also that I am talking about servers with more than 2 NICs means also that this server are well tuned (for my understandings) and with more than 2GB of RAM, SCSI UW-320 Adaptec and HD-UW320 and > 2Ghz CPUs there are appearently several issues on IPFW for FBSD 5.2 and above which are not resolved (natd,divert,ipfw count etc ...) even if I do not have exact data I believe on my experience and especially stats that the performance on 4.11 is superiour to 5.x On this special issue for MySQL I say: FBSd 5.x gets slowwww with DB-tables over 10MB and 4.11 does not care, query fast (and here does matter your personal .cf config) anyway, seams for me that FBSD5.x is slow on any larger throughput, fs or nic does not matter and generally 5.x as router/gw do not even get close to 4.11 My experience is on almost 500 servers we have from 1 to 8 MB sustained througput each and we tried to migrate to 5.x about more than 6 month On Mailservers ore any dedicated server with singleNIC I do *_NOT_* experience this difficulty[ies] and get sustained throughputs of 8-10MB/s without any problem. \Hans -- WIPNET Telecom Ltda. http://wip.mega.net.br http://wip.mega.net.br/tec.asc A mensagem foi scaneada pelo sistema de e-mail e pode ser considerada segura. Service fornecido pelo Datacenter Matik https://datacenter.matik.com.br