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 DF99DD1D66C for ; Fri, 13 Feb 2004 12:38:57 +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 64605-02 for ; Fri, 13 Feb 2004 08:38:59 -0400 (AST) Received: from fep03-mail.bloor.is.net.cable.rogers.com (fep03-mail.bloor.is.net.cable.rogers.com [66.185.86.73]) by svr1.postgresql.org (Postfix) with ESMTP id 8B243D1D642 for ; Fri, 13 Feb 2004 08:38:55 -0400 (AST) Received: from phlogiston.dydns.org ([65.49.121.67]) by fep03-mail.bloor.is.net.cable.rogers.com (InterMail vM.5.01.05.12 201-253-122-126-112-20020820) with ESMTP id <20040213123858.OLSU189272.fep03-mail.bloor.is.net.cable.rogers.com@phlogiston.dydns.org> for ; Fri, 13 Feb 2004 07:38:58 -0500 Received: by phlogiston.dydns.org (Postfix, from userid 1000) id E85173F3A; Fri, 13 Feb 2004 07:38:57 -0500 (EST) Date: Fri, 13 Feb 2004 07:38:57 -0500 From: Andrew Sullivan To: pgsql-performance@postgresql.org Subject: Re: Disappointing performance in db migrated from MS SQL Server Message-ID: <20040213123857.GF2222@phlogiston.dyndns.org> Mail-Followup-To: pgsql-performance@postgresql.org References: <200402121905.i1CJ5XW13096@candle.pha.pa.us> <200402121719.27666.chris@ruprecht.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200402121719.27666.chris@ruprecht.org> User-Agent: Mutt/1.5.4i X-Authentication-Info: Submitted using SMTP AUTH LOGIN at fep03-mail.bloor.is.net.cable.rogers.com from [65.49.121.67] using ID at Fri, 13 Feb 2004 07:38:58 -0500 X-Virus-Scanned: by amavisd-new at postgresql.org X-Archive-Number: 200402/155 X-Sequence-Number: 5679 On Thu, Feb 12, 2004 at 05:19:27PM -0500, Chris Ruprecht wrote: > what he's doing, this might be a bottleneck. I don't like the virtual memory > strategy of Linux too much and would rather increase this to 1 - 2 GB for the > Postgres DB - Specially since he's not running anything else on the machine > and he has 4 GB to play with. Have you ever had luck with 2G of shared memory? When I have tried that, the system is very fast initially, and gradually slows to molasses-like speed. My hypothesis is that the cache-lookup logic isn't that smart, and so is inefficient either when using the cache or when doing cache maintenance. A -- Andrew Sullivan