From owner-freebsd-current@FreeBSD.ORG Fri Aug 12 14:07:07 2005 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E943016A420; Fri, 12 Aug 2005 14:07:07 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: from mv.twc.weather.com (mv.twc.weather.com [65.212.71.225]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7506043D48; Fri, 12 Aug 2005 14:07:07 +0000 (GMT) (envelope-from jhb@FreeBSD.org) Received: from [10.50.40.201] (Not Verified[65.202.103.25]) by mv.twc.weather.com with NetIQ MailMarshal (v6, 0, 3, 8) id ; Fri, 12 Aug 2005 10:21:58 -0400 From: John Baldwin To: freebsd-current@freebsd.org Date: Fri, 12 Aug 2005 09:43:28 -0400 User-Agent: KMail/1.8 References: <20050812093841.GA11814@frontfree.net> In-Reply-To: <20050812093841.GA11814@frontfree.net> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-6" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200508120943.29376.jhb@FreeBSD.org> Cc: freebsd-stable@freebsd.org Subject: Re: [RELENG_6] idle thread statistics not correct? 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: Fri, 12 Aug 2005 14:07:08 -0000 On Friday 12 August 2005 05:38 am, Xin LI wrote: > Hi, all, > > I got into a strange issue on a remote box I just upgraded to RELENG_6. > > [delphij@www] ~> ps aux | grep idle | grep -v grep > root 11 92.5 0.0 0 8 ?? RL Thu03AM 0:00.00 [idle: > cpu3] root 13 92.5 0.0 0 8 ?? RL Thu03AM 2293:59.13 > [idle: cpu1] root 12 70.7 0.0 0 8 ?? RL Thu03AM > 2300:52.77 [idle: cpu2] root 14 27.8 0.0 0 8 ?? RL > Thu03AM 2292:59.84 [idle: cpu0] > > However, if I set machdep.hlt_logical_cpus=0, the ps aux output looks more > rational: > > [delphij@www] ~> ps aux | grep idle | grep -v grep > root 11 92.5 0.0 0 8 ?? RL Thu03AM 2307:08.09 [idle: > cpu3] root 13 81.2 0.0 0 8 ?? RL Thu03AM 2306:58.61 > [idle: cpu1] root 12 57.1 0.0 0 8 ?? RL Thu03AM > 2304:56.66 [idle: cpu2] root 14 39.1 0.0 0 8 ?? RL > Thu03AM 2294:48.68 [idle: cpu0] > > I have not looked into this deeply yet, but I think this really looks weird > and may indicate other issues. [ Grrr, stupid kmail "smart" quoting always screws up formatted output, wish I could turn it off ] The idle CPUs are idle in such a way that they don't update their stats is all. It's not an indication of any other issues, it's simply an accounting error in that one edge case. I can look into fixing it but since it's just cosmetic, it's fairly low on the priority list. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve" = http://www.FreeBSD.org