From owner-freebsd-stable@FreeBSD.ORG Wed Apr 6 18:43:17 2005 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2BB1A16A4CE; Wed, 6 Apr 2005 18:43:17 +0000 (GMT) Received: from www.cryptography.com (li-22.members.linode.com [64.5.53.22]) by mx1.FreeBSD.org (Postfix) with ESMTP id D156943D58; Wed, 6 Apr 2005 18:43:16 +0000 (GMT) (envelope-from nate@root.org) Received: from [10.0.0.34] (adsl-67-119-74-222.dsl.sntc01.pacbell.net [67.119.74.222]) by www.cryptography.com (8.12.8/8.12.8) with ESMTP id j36IhFLS025014 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT); Wed, 6 Apr 2005 11:43:16 -0700 Message-ID: <42542DC2.70405@root.org> Date: Wed, 06 Apr 2005 11:43:14 -0700 From: Nate Lawson User-Agent: Mozilla Thunderbird 1.0 (Windows/20041206) X-Accept-Language: en-us, en MIME-Version: 1.0 To: Pierre-Luc Drouin References: <200504040609.j3469g7b001419@drjekyll.mkbuelow.net> <425425BC.6080006@pldrouin.net> <42542C6F.6010508@root.org> <42542D03.7050007@pldrouin.net> In-Reply-To: <42542D03.7050007@pldrouin.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit cc: Greg 'groggy' Lehey cc: Christian Brueffer cc: freebsd-stable@freebsd.org cc: Matthias Buelow Subject: Re: 5.4-prerelease - hanging under load X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 06 Apr 2005 18:43:17 -0000 Pierre-Luc Drouin wrote: > Nate Lawson wrote: > >> Pierre-Luc Drouin wrote: >> >>> Matthias Buelow wrote: >>> >>>> Nate Lawson writes: >>>> >>>> >>>> >>>>> sysctl dev.cpu and look at the current frequency setting. If low, >>>>> then your system is affected and will be fixed soon when I mfc. If >>>>> not, perhaps you have an interrupt storm (vmstat -i) >>>>> >>>> >>>> >>>> >>>> >>>> Just for the record. I ran vmstat -i in a loop while untarring the >>>> thunderbird source (causing degraded interactive responsiveness, as >>>> reported in an earlier mail), and couldn't see any noticable >>>> increase in >>>> interrupt rate. >>>> >>>> mkb. >>>> >>>> >>>> >>> I've noticed that the idle process is using sometimes as much as 60% >>> of my CPU. Could it be a relation between that and the lag we have >>> with 5.4? >> >> >> >> That is different. sysctl hw.acpi.cpu.cx_lowest="C1" to see if that >> works around it. >> > I already have this Then it's not acpi since c1 is the old (even 4.x) behavior. -- Nate