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 E96893A5EE3 for ; Thu, 27 Jan 2005 16:57:05 +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 84015-03 for ; Thu, 27 Jan 2005 16:57:00 +0000 (GMT) Received: from davinci.ethosmedia.com (server227.ethosmedia.com [209.128.84.227]) by svr1.postgresql.org (Postfix) with ESMTP id 8C0873A5EA3 for ; Thu, 27 Jan 2005 16:56:59 +0000 (GMT) X-EthosMedia-Virus-Scanned: no infections found Received: from [63.195.55.98] (account josh@agliodbs.com HELO spooky) by davinci.ethosmedia.com (CommuniGate Pro SMTP 4.1.8) with ESMTP id 6957581; Thu, 27 Jan 2005 08:58:42 -0800 From: Josh Berkus Organization: Aglio Database Solutions To: pgsql-performance@postgresql.org Subject: Re: Ideal disk setup for Postgresql 7.4? Date: Thu, 27 Jan 2005 08:56:03 -0800 User-Agent: KMail/1.6.2 Cc: Steve Poe References: <41F63424.1060904@sfnet.cc> <200501261849.15176.josh@agliodbs.com> <41F82CA2.5070604@sfnet.cc> In-Reply-To: <41F82CA2.5070604@sfnet.cc> MIME-Version: 1.0 Content-Disposition: inline Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <200501270856.03632.josh@agliodbs.com> X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.014 tagged_above=0 required=5 tests=AWL X-Spam-Level: X-Archive-Number: 200501/544 X-Sequence-Number: 10234 Steve, > You mentioned earlier that to get around the CS bug, avoid the query > structures which trigger it. Dumb question: How do you isolate this? In real terms, it's generally triggered by a query joining against a very large table requiring a seq scan. You can probably find the "bad queries" just by using PQA, and looking for select, delete and update queries which last over 60 seconds. > Is there a way in a Postgresql query to only look at 1 processor only in > a dual-CPU setup? That would be an OS question. I personally can't see how. > Any likelyhood this CS storm will be understood in the next couple months? It's well understood. See the archives of this list. The problem is that implementing the solution is very, very hard -- 100+ hours from a top-notch programmer. I'm still hoping to find a corporate sponsor for the issue ... -- Josh Berkus Aglio Database Solutions San Francisco