Received: from localhost (maia-2.hub.org [200.46.204.187]) by postgresql.org (Postfix) with ESMTP id 028D39FA474 for ; Wed, 6 Dec 2006 16:33:06 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.187]) (amavisd-new, port 10024) with ESMTP id 53793-06-2 for ; Wed, 6 Dec 2006 16:32:52 -0400 (AST) X-Greylist: delayed 00:20:08.088673 by SQLgrey-1.7.4 Received: from larry.aptalaska.net (larry.aptalaska.net [64.186.96.3]) by postgresql.org (Postfix) with ESMTP id B80CD9FA49D for ; Wed, 6 Dec 2006 16:32:55 -0400 (AST) Received: from [192.168.98.9] (rdbck-static-287.palmer.mtaonline.net [64.4.232.33]) (authenticated bits=0) by larry.aptalaska.net (8.13.8/8.13.6) with ESMTP id kB6KCbeB005477 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Wed, 6 Dec 2006 11:12:37 -0900 Message-ID: <45772446.4010301@aptalaska.net> Date: Wed, 06 Dec 2006 11:12:54 -0900 From: Matthew Schumacher User-Agent: Thunderbird 1.5.0.8 (X11/20061025) MIME-Version: 1.0 To: pgsql-performance@postgresql.org Subject: Disk storage and san questions (was File Systems Compared) X-Enigmail-Version: 0.94.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-DNS-Reverse: Passed - Reverse DNS of rdbck-static-287.palmer.mtaonline.net X-Spam-Bayes: Learn: ham X-Scanned-By: MIMEDefang 2.58 on 64.186.96.3 X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=0 tagged_above=0 required=5 tests=BAYES_50, SPF_PASS X-Spam-Level: X-Archive-Number: 200612/152 X-Sequence-Number: 22208 Joshua D. Drake wrote: > I agree. I have many people that want to purchase a SAN because someone > told them that is what they need... Yet they can spend 20% of the cost > on two external arrays and get incredible performance... > > We are seeing great numbers from the following config: > > (2) HP MS 30s (loaded) dual bus > (2) HP 6402, one connected to each MSA. > > The performance for the money is incredible. This raises some questions for me. I just budgeted for a san because I need lots of storage for email/web systems and don't want to have a bunch of local disks in each server requiring each server to have it's own spares. The idea is that I can have a platform wide disk chassis which requires only one set of spares and run my linux hosts diskless. Since I am planing on buying the sanraid iscsi solution I would simply boot hosts with pxelinux and pass a kernel/initrd image that would mount the iscsi target as root. If a server fails, I simply change the mac address in the bootp server then bring up a spare in it's place. Now that I'm reading these messages about disk performance and sans, it's got me thinking that this solution is not ideal for a database server. Also, it appears that there are several people on the list that have experience with sans so perhaps some of you can fill in some blanks for me: 1. Is iscsi a decent way to do a san? How much performance do I loose vs connecting the hosts directly with a fiber channel controller? 2. Would it be better to omit my database server from the san (or at least the database storage) and stick with local disks? If so what disks/controller card do I want? I use dell servers for everything so it would be nice if the recommendation is a dell system, but doesn't need to be. Overall I'm not very impressed with the LSI cards, but I'm told the new ones are much better. 3. Anyone use the sanrad box? Is it any good? Seems like consolidating disk space and disk spares platform wide is good idea, but I've not used a san before so I'm nervous about it. 4. What would be the performance of SATA disks in a JBOD? If I got 8 200g disks and made 4 raid one mirrors in the jbod then striped them together in the sanraid would that perform decent? Is there an advantage splitting up raid 1+0 across the two boxes, or am I better doing raid 1+0 in the jbod and using the sanrad as an iscsi translator? Thats enough questions for now.... Thanks, schu