From owner-freebsd-current@FreeBSD.ORG Mon Dec 10 21:51:35 2007 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2B15616A4A0 for ; Mon, 10 Dec 2007 21:51:35 +0000 (UTC) (envelope-from sam@errno.com) Received: from ebb.errno.com (ebb.errno.com [69.12.149.25]) by mx1.freebsd.org (Postfix) with ESMTP id F117E13C4E7 for ; Mon, 10 Dec 2007 21:51:34 +0000 (UTC) (envelope-from sam@errno.com) Received: from trouble.errno.com (trouble.errno.com [10.0.0.248]) (authenticated bits=0) by ebb.errno.com (8.13.6/8.12.6) with ESMTP id lBALpSow036547 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO); Mon, 10 Dec 2007 13:51:29 -0800 (PST) (envelope-from sam@errno.com) Message-ID: <475DB4E0.3060401@errno.com> Date: Mon, 10 Dec 2007 13:51:28 -0800 From: Sam Leffler User-Agent: Thunderbird 2.0.0.9 (X11/20071125) MIME-Version: 1.0 To: Poul-Henning Kamp References: <28655.1197320193@critter.freebsd.dk> In-Reply-To: <28655.1197320193@critter.freebsd.dk> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-DCC-Rhyolite-Metrics: o.com; whitelist Cc: Martin Cracauer , freebsd-current@freebsd.org, Thomas Sparrevohn Subject: Re: CURRENT Kernel makes the system run very very hot X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 10 Dec 2007 21:51:35 -0000 Poul-Henning Kamp wrote: > In message <20071210201106.GB90158@cons.org>, Martin Cracauer writes: > > I installed this on my laptop yesterday: > > FreeBSD critter.freebsd.dk 8.0-CURRENT FreeBSD 8.0-CURRENT > #0: Sun Dec 9 10:41:25 UTC 2007 > root@critter.freebsd.dk:/usr/obj/freebsd/src/sys/C5 i386 > > And it does indeed look like the idle threads do not HLT the cpu. > > Interestingly, powerd(8) does the right thing and throttles down > the cpu clock even though the idle threads churn away. > > top -HS shows: > > PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU COMMAND > 10 root 171 ki31 0K 16K CPU1 1 25.2H 100.00% {idle: cpu1} > 10 root 171 ki31 0K 16K RUN 0 25.2H 95.36% {idle: cpu0} > 928 phk 45 0 319M 68624K *Giant 0 42:46 0.98% Xorg > 28654 phk 44 0 3540K 1552K CPU1 0 0:01 0.98% top > 982 phk 44 0 6500K 3940K select 1 11:03 0.29% xterm > 11 root -24 - 0K 112K WAIT 1 19:49 0.00% {swi6: task queu > This might also explain why I started to see buildworld overheat my t41 where previously I'd built world countless times w/o an issue. The only good thing that came out of that was that I verified thermal shutdown worked correctly and it uncovered a bug in acpi where a failed read would cause acpi to fall over (still unfixed). Sam