X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.144]) by svr1.postgresql.org (Postfix) with ESMTP id 3D76C3A1AC1 for ; Fri, 14 Jan 2005 16:29:43 +0000 (GMT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 86055-05 for ; Fri, 14 Jan 2005 16:29:33 +0000 (GMT) Received: from stark.xeocode.com (gsstark.mtl.istop.com [66.11.160.162]) by svr1.postgresql.org (Postfix) with ESMTP id 5D5263A18A7 for ; Fri, 14 Jan 2005 16:29:32 +0000 (GMT) Received: from localhost ([127.0.0.1] helo=stark.xeocode.com) by stark.xeocode.com with smtp (Exim 3.36 #1 (Debian)) id 1CpUK8-0000se-00; Fri, 14 Jan 2005 11:29:21 -0500 To: Jan Dittmer Cc: "Joshua D. Drake" , Christopher Browne , pgsql-performance@postgresql.org Subject: Re: which dual-CPU hardware/OS is fastest for PostgreSQL? References: <59b2d39b05011018421680264b@mail.gmail.com> <41E3569A.4030102@commandprompt.com> <41E3A780.3020505@portrix.net> In-Reply-To: <41E3A780.3020505@portrix.net> From: Greg Stark Organization: The Emacs Conspiracy; member since 1992 Date: 14 Jan 2005 11:29:20 -0500 Message-ID: <87is60ug7z.fsf@stark.xeocode.com> Lines: 19 User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.3 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.055 tagged_above=0 required=5 tests=AWL, FORGED_RCVD_HELO X-Spam-Level: X-Archive-Number: 200501/188 X-Sequence-Number: 9878 Jan Dittmer writes: > You could always do raid 1 over raid 0, with newer kernels (2.6ish) > there is even a dedicated raid10 driver. Aren't you much better off doing raid 0 over raid 1? With raid 1 over raid 0 you're mirroring two stripe sets. That means if any drive from the first stripe set goes you lose the whole side of the mirror. If any drive of the second stripe set goes you lost your array. Even if they're not the same position in the array. If you do raid 0 over raid 1 then you're striping a series of mirrored drives. So if any drive fails you only lose that drive from the stripe set. If another drive fails then you're ok as long as it isn't the specific drive that was paired with the first failed drive. -- greg