X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (unknown [200.46.204.2]) by svr1.postgresql.org (Postfix) with ESMTP id BD658D1DC52 for ; Wed, 3 Mar 2004 20:46:59 +0000 (GMT) Received: from svr1.postgresql.org ([200.46.204.71]) by localhost (neptune.hub.org [200.46.204.2]) (amavisd-new, port 10024) with ESMTP id 85586-03 for ; Wed, 3 Mar 2004 16:46:59 -0400 (AST) Received: from www.postgresql.com (www.postgresql.com [200.46.204.209]) by svr1.postgresql.org (Postfix) with ESMTP id CDE1BD1DF80 for ; Wed, 3 Mar 2004 16:46:51 -0400 (AST) Received: from davinci.ethosmedia.com (server228.ethosmedia.com [209.128.84.228]) by www.postgresql.com (Postfix) with ESMTP id ADBFCCF4D2F for ; Wed, 3 Mar 2004 16:46:48 -0400 (AST) Received: from [63.195.55.98] (HELO 192.168.1.29) by davinci.ethosmedia.com (CommuniGate Pro SMTP 4.0.2) with ESMTP id 4534138; Wed, 03 Mar 2004 11:11:25 -0800 From: Josh Berkus Reply-To: josh@agliodbs.com Organization: Aglio Database Solutions To: johnnnnnn , "scott.marlowe" Subject: Re: Scaling further up Date: Wed, 3 Mar 2004 11:09:23 -0800 User-Agent: KMail/1.5.4 Cc: pgsql-performance@postgresql.org References: <4BAFBB6B9CC46F41B2AD7D9F4BBAF785098039@vt-pe2550-001.vantage.vantage.com> <20040302232540.GA4102@performics.com> In-Reply-To: <20040302232540.GA4102@performics.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200403031109.23201.josh@agliodbs.com> X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200403/44 X-Sequence-Number: 5900 John, > This would imply that an upgrade in drive RPM should be accompanied by > a decrease in random_page_cost, correct? Maybe. Maybe not. Tom's Hardware did some Bonnie++ testing with a variety of new drives last year. They were moderately surprised to find that there were "faster" drives (i.e. higher RPM) which had lower real throughput due to poor onboard software and hardware, such as a small and slow onboard cache. So, it would be reasonable to assume that a 10,000 RPM Barracuda could support marginally lower random_page_cost than a 7,200 RPM Barracuda ... but that tells you nothing about a 10,000 RPM Maxtor Diamond (as an example). Also, many other factors influence real random_page_cost; the size and access pattern of your database is probably much more important than your RPM. -- -Josh Berkus Aglio Database Solutions San Francisco