From owner-freebsd-stable Thu Dec 30 22:21:54 1999 Delivered-To: freebsd-stable@freebsd.org Received: from mass.cdrom.com (castles532.castles.com [208.214.165.96]) by hub.freebsd.org (Postfix) with ESMTP id 2F92E154AC for ; Thu, 30 Dec 1999 22:21:51 -0800 (PST) (envelope-from msmith@mass.cdrom.com) Received: from mass.cdrom.com (localhost [127.0.0.1]) by mass.cdrom.com (8.9.3/8.9.3) with ESMTP id WAA00576; Thu, 30 Dec 1999 22:27:02 -0800 (PST) (envelope-from msmith@mass.cdrom.com) Message-Id: <199912310627.WAA00576@mass.cdrom.com> X-Mailer: exmh version 2.1.1 10/15/1999 To: tsikora@powerusersbbs.com Cc: "freebsd-stable@FreeBSD.ORG" Subject: Re: Temperature Findings In-reply-to: Your message of "Thu, 30 Dec 1999 19:20:26 EST." <386BF6CA.EA00DF5C@home.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Thu, 30 Dec 1999 22:27:02 -0800 From: Mike Smith Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > I had one my technicians set up a scope to test the voltage readings and > a Cooper temperature gauge to check the case temp. We decided to abandon > the CPU test since we had no accurate way to attach the gauge. Our > findings: > The voltage readings by the winbond IC in the bios are accurate. > The case temperature was 5F cooler than reported. > So I would conclude the readings from the bios are a fairly accurate > representation of the machines current condition. > > Things I failed to mention. > The CPU's were overclocked by 100MHz > Core CPU Voltage was raised a 1/2 step to 2.05V > > o This still does not explain the differences between Linux > and FreeBSD. The difference has already been explained as a different instruction mix. This should be obvious to anyone that has been in the industry for as long as you have. > o The standard 3.3-RELEASE UniProcessor kernel runs identical to > Linux. This is because both systems use the HLT instruction, which has a low power consumption. You've already been told this. > o FreeBSD SMP kernels immediately run hotter than the standard > kernel. FreeBSD doesn't use HLT in the SMP implementation. You've been told this as well. > I put Core voltage back to normal and set the CPU's to standard > settings. The result was much better but it still runs about 14 degrees > hotter.(acceptable) 26 degrees was not. > > Has anyone else checked this. Just checking the Generic versus a SMP > kernel you should see this. This is commonly known behaviour. Your problem is simply that your cooling setup is not adequate to support your system running at 100% duty cycle. You've been told this already. You need to upgrade your cooling arrangements, and you've been told _that_ already too. -- \\ Give a man a fish, and you feed him for a day. \\ Mike Smith \\ Tell him he should learn how to fish himself, \\ msmith@freebsd.org \\ and he'll hate you for a lifetime. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message