From owner-freebsd-stable@FreeBSD.ORG Fri Jun 17 21:01:21 2005 Return-Path: X-Original-To: freebsd-stable@freebsd.org Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 19A2616A41C for ; Fri, 17 Jun 2005 21:01:21 +0000 (GMT) (envelope-from mkb@mkbuelow.net) Received: from luzifer.incubus.de (incubus.de [80.237.207.83]) by mx1.FreeBSD.org (Postfix) with ESMTP id C42DC43D49 for ; Fri, 17 Jun 2005 21:01:20 +0000 (GMT) (envelope-from mkb@mkbuelow.net) Received: from drjekyll.mkbuelow.net (p54AAEB90.dip.t-dialin.net [84.170.235.144]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by luzifer.incubus.de (Postfix) with ESMTP id 059EC2EFF0; Fri, 17 Jun 2005 23:04:11 +0200 (CEST) Received: from drjekyll.mkbuelow.net (mkb@localhost.mkbuelow.net [127.0.0.1]) by drjekyll.mkbuelow.net (8.13.3/8.13.3) with ESMTP id j5HL1Upn043700; Fri, 17 Jun 2005 23:01:31 +0200 (CEST) (envelope-from mkb@drjekyll.mkbuelow.net) Message-Id: <200506172101.j5HL1Upn043700@drjekyll.mkbuelow.net> From: Matthias Buelow To: David Sze In-Reply-To: Message from David Sze of "Fri, 17 Jun 2005 13:57:26 CDT." <20050617185726.GD94284@mail.distrust.net> X-Mailer: MH-E 7.84; nmh 1.0.4; XEmacs 21.4 (patch 17) Date: Fri, 17 Jun 2005 23:01:30 +0200 Sender: mkb@mkbuelow.net Cc: freebsd-stable@freebsd.org, Greg Barniskis , uzi@bmby.com, Matthias Buelow Subject: Re: FreeBSD MySQL still WAY slower than Linux X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 17 Jun 2005 21:01:21 -0000 David Sze writes: >I'm not sure filesystem consistency alone is "good enough". Say your >bank's database crashes right after you make a deposit. When it comes >back up it's consistent, but only up to 5 minutes before the crash due >to the async mount. A bank doesn't run on Unix. It runs on mainframes, with such funny features like processors executing each instruction in parallel, and comparing the results. Completely different universe here. On Unix, filesystem consistency is the best you'll normally get. You _can_ mount filesystems synchronously, both with UFS aswell as ext2/3 etc., but the performance is abysmal. Maybe useful in particular situations but you probably wouldn't want to run your desktop (or busy server) with it. I mean, just try it and see (and make sure writeback-caching on the disks is disabled, when possible.) mkb.