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 37146329FD7 for ; Thu, 7 Oct 2004 19:15:50 +0100 (BST) 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 57108-06 for ; Thu, 7 Oct 2004 18:15:39 +0000 (GMT) Received: from mail3.panix.com (mail3.panix.com [166.84.1.74]) by svr1.postgresql.org (Postfix) with ESMTP id 1A5B8329F32 for ; Thu, 7 Oct 2004 19:15:39 +0100 (BST) Received: from panix2.panix.com (panix2.panix.com [166.84.1.2]) by mail3.panix.com (Postfix) with ESMTP id 3638F981E9; Thu, 7 Oct 2004 14:15:38 -0400 (EDT) Received: (from adler@localhost) by panix2.panix.com (8.11.6p2-a/8.8.8/PanixN1.1) id i97IFcB14523; Thu, 7 Oct 2004 14:15:38 -0400 (EDT) Date: Thu, 7 Oct 2004 14:15:38 -0400 From: Michael Adler To: Bill Montgomery Cc: Alan Stange , Gaetano Mendola , pgsql-performance@postgresql.org Subject: Re: Excessive context switching on SMP Xeons Message-ID: <20041007181537.GA1693@pobox.com> References: <4162CA14.6080206@lulu.com> <200410050947.36174.josh@agliodbs.com> <41630D50.3020308@lulu.com> <200410051538.51664.josh@agliodbs.com> <41636D8E.1090403@rentec.com> <41648446.5020102@bigfoot.com> <4164B48C.9060202@rentec.com> <41656559.70100@lulu.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <41656559.70100@lulu.com> User-Agent: Mutt/1.4.2.1i X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, hits=0.0 tagged_above=0.0 required=5.0 tests= X-Spam-Level: X-Archive-Number: 200410/87 X-Sequence-Number: 8563 On Thu, Oct 07, 2004 at 11:48:41AM -0400, Bill Montgomery wrote: > Alan Stange wrote: > > The same test on a Dell PowerEdge 1750, Dual Xeon 3.2 GHz, 512k cache, > HT on, Linux 2.4.21-20.ELsmp (RHEL 3), 4GB memory, pg 7.4.5: > > Far less performance that the Dual Opterons with a low number of > clients, but the gap narrows as the number of clients goes up. Anyone > smarter than me care to explain? You'll have to wait for someone smarter than you, but I will posit this: Did you use a tmpfs filesystem like Alan? You didn't mention either way. Alan did that as an attempt remove IO as a variable. -Mike