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 7DA453A3CE1 for ; Mon, 3 Jan 2005 20:36:29 +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 07835-04 for ; Mon, 3 Jan 2005 20:36:15 +0000 (GMT) Received: from stark.xeocode.com (gsstark.mtl.istop.com [66.11.160.162]) by svr1.postgresql.org (Postfix) with ESMTP id 237AF3A3B5B for ; Mon, 3 Jan 2005 20:36:16 +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 1ClYvw-00089T-00; Mon, 03 Jan 2005 15:36:08 -0500 To: Madison Kelly Cc: pgsql-performance@postgresql.org Subject: Re: Hardware purchase question References: <6.0.1.1.0.20041124114556.04b7cc80@mail.marketingsolutionsinc.com> <41BDD001.8070701@commandprompt.com> <330532b6050103112034cf47c8@mail.gmail.com> <41D99E7E.3080704@alteeve.com> In-Reply-To: <41D99E7E.3080704@alteeve.com> From: Greg Stark Organization: The Emacs Conspiracy; member since 1992 Date: 03 Jan 2005 15:36:07 -0500 Message-ID: <87wtuu6yiw.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=0.049 tagged_above=0 required=5 tests=AWL, FORGED_RCVD_HELO X-Spam-Level: X-Archive-Number: 200501/25 X-Sequence-Number: 9715 Madison Kelly writes: > Without it, specially in a failure state, the performance can collapse as > the CPU performs all that extra math. It's really not the math that makes raid 5 hurt. It's that in order to calculate the checksum block the raid controller needs to read in the existing checksum block and write out the new version. So every write causes not just one drive seeking and writing, but a second drive seeking and performing a read and a write. The usual strategy for dealing with that is stuffing a huge nonvolatile cache in the controller so those reads are mostly cached and the extra writes don't saturate the i/o throughput. But those kinds of controllers are expensive and not an option for software raid. -- greg