From owner-freebsd-stable@FreeBSD.ORG Mon May 3 22:48:17 2010 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 53FF31065670 for ; Mon, 3 May 2010 22:48:17 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta12.westchester.pa.mail.comcast.net (qmta12.westchester.pa.mail.comcast.net [76.96.59.227]) by mx1.freebsd.org (Postfix) with ESMTP id 022E78FC08 for ; Mon, 3 May 2010 22:48:16 +0000 (UTC) Received: from omta21.westchester.pa.mail.comcast.net ([76.96.62.72]) by qmta12.westchester.pa.mail.comcast.net with comcast id D2vR1e0051ZXKqc5CAoH0o; Mon, 03 May 2010 22:48:17 +0000 Received: from koitsu.dyndns.org ([98.248.46.159]) by omta21.westchester.pa.mail.comcast.net with comcast id DAoG1e0053S48mS3hAoGjz; Mon, 03 May 2010 22:48:17 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id C24899B425; Mon, 3 May 2010 15:48:14 -0700 (PDT) Date: Mon, 3 May 2010 15:48:14 -0700 From: Jeremy Chadwick To: Bryce Edwards Message-ID: <20100503224814.GA9477@icarus.home.lan> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.20 (2009-06-14) Cc: freebsd-stable@freebsd.org Subject: Re: 8-STABLE performance issues on Supermicro Core i7 X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 03 May 2010 22:48:17 -0000 On Sun, May 02, 2010 at 09:40:13PM -0500, Bryce Edwards wrote: > I've got a new Supermicro X58 system with an Intel Core i7 930 with 6 > GB ram that is not performing nearly as fast as it should in many ways > (compiling, network transfers). By the way, an interesting thread you might read -- yes it's long. Subject "Only 70% of theoretical peak performance on FreeBSD 8/amd64, Corei7 920": http://lists.freebsd.org/pipermail/freebsd-stable/2010-April/thread.html#56253 The performance stats you're providing are much lower than 70% peak, so I'm not sure there's a correlation, but that's a thread which did bring up odd performance-affecting changes in the i5/i7 architecture: http://lists.freebsd.org/pipermail/freebsd-stable/2010-April/056332.html It's also hard to determine from the thread given its length, but I believe pinning a process to an individual CPU increased (~20%+) the OPs performance. http://lists.freebsd.org/pipermail/freebsd-stable/2010-April/056316.html http://lists.freebsd.org/pipermail/freebsd-stable/2010-April/056339.html -- | Jeremy Chadwick jdc@parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB |