From owner-freebsd-stable@FreeBSD.ORG Wed Apr 6 18:40:04 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 A4B4816A4CE; Wed, 6 Apr 2005 18:40:04 +0000 (GMT) Received: from relais.videotron.ca (relais.videotron.ca [24.201.245.36]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5F6DC43D2D; Wed, 6 Apr 2005 18:40:04 +0000 (GMT) (envelope-from pldrouin@pldrouin.net) Received: from [24.200.248.78] by VL-MO-MR010.ip.videotron.ca (iPlanet Messaging Server 5.2 HotFix 1.21 (built Sep 8 2003)) with ESMTP id <0IEJ00LGBFURA6@VL-MO-MR010.ip.videotron.ca>; Wed, 06 Apr 2005 14:40:04 -0400 (EDT) Date: Wed, 06 Apr 2005 14:40:03 -0400 From: Pierre-Luc Drouin In-reply-to: <42542C6F.6010508@root.org> To: Nate Lawson Message-id: <42542D03.7050007@pldrouin.net> MIME-version: 1.0 Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT X-Accept-Language: en-us, en User-Agent: Mozilla Thunderbird 1.0.2 (X11/20050403) References: <200504040609.j3469g7b001419@drjekyll.mkbuelow.net> <425425BC.6080006@pldrouin.net> <42542C6F.6010508@root.org> 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 18:40:04 -0000 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