From owner-freebsd-current@FreeBSD.ORG Sun Jan 24 16:29:18 2010 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 651061065672 for ; Sun, 24 Jan 2010 16:29:18 +0000 (UTC) (envelope-from asmrookie@gmail.com) Received: from mail-iw0-f200.google.com (mail-iw0-f200.google.com [209.85.223.200]) by mx1.freebsd.org (Postfix) with ESMTP id 278988FC17 for ; Sun, 24 Jan 2010 16:29:18 +0000 (UTC) Received: by mail-iw0-f200.google.com with SMTP id 38so2332432iwn.11 for ; Sun, 24 Jan 2010 08:29:18 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:sender:received:in-reply-to :references:date:x-google-sender-auth:message-id:subject:from:to:cc :content-type:content-transfer-encoding; bh=jKEbx4OUN9c7wNmSkyV5KARW9UP8c1pwm9eEf02ngnY=; b=DVQc/52XtuhBIrxYM7tfMzab+htYiu4mMNRYSinADHtx+eqDRjkd/POJ8qeYNrUhrf tiZjBM7IxqUTEdDSA59cGwYNKtLU5rl4v8kP2Zy6RT4RkyKiKCEmTabCg8jspfa0Z/X9 MZ2vKZqxEehIn90k3yl9C+i63hsU7mvkPZ5Ys= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=R9BFvYrpQ9aQj3xWFHaKCt1aOGFYeW2b5vI/TDPiWZ+tOqj+M6yk5mw5RvcBA95PR6 4dF/Qgdf9o3NG27Qp7wxfnZKKyGwCgkG1gtXXea3bARx89CbYeJKAXIBVM8cxYYfryVO ok59h7OULGNj3W3wGvaRD66RcDVaHB4aRkmEc= MIME-Version: 1.0 Sender: asmrookie@gmail.com Received: by 10.231.59.7 with SMTP id j7mr676647ibh.12.1264350557286; Sun, 24 Jan 2010 08:29:17 -0800 (PST) In-Reply-To: References: <20100124024214.GA49252@Fluffy.Khv.RU> <4B5BC039.5060406@logvinov.com> Date: Sun, 24 Jan 2010 17:29:17 +0100 X-Google-Sender-Auth: 16474e0be0ef8c6b Message-ID: <3bbf2fe11001240829k46d62476pda54d149c39ae7c3@mail.gmail.com> From: Attilio Rao To: Richard Todd Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: fluffy@fluffy.khv.ru, freebsd-current@freebsd.org, Alexander Logvinov Subject: Re: Regression in -current? 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: Sun, 24 Jan 2010 16:29:18 -0000 2010/1/24 Richard Todd : > Alexander Logvinov writes: > >> Hello! >> >> On 24.01.2010 10:43 Dima Panov wrote: >>> I see a strange regression since Friday's kernel, may be it's a kqueue-= related. >>> While building ports, now I never see 100% load of cpu, and portupgrade= -fa >>> takes ~7 hours for ~40 ports. Updating to current state (~3am VLAT) doe= sn't help. >>> >>> KDB and WITNESS/INVARIANTS disablen in kernel config > >> =C2=A0I have a similar problem with r202904 amd64 kernel with interestin= g CPU >> statistic: >> >> top output: >> >> last pid: =C2=A01885; =C2=A0load averages: =C2=A02.89, =C2=A01.56, =C2= =A00.66 =C2=A0 =C2=A0up 0+00:02:47 >> 09:31:44 >> 72 processes: =C2=A03 running, 69 sleeping >> _CPU: =C2=A00.0% user, =C2=A00.0% nice, =C2=A00.0% system, =C2=A00.0% in= terrupt, =C2=A00.0% idle_ >> Mem: 120M Active, 39M Inact, 153M Wired, 6968K Cache, 65M Buf, 3565M Fre= e >> Swap: 8192M Total, 8192M Free > > Yeah, I saw the same thing on my core2duo system (running in amd64 mode, > dunno if that makes a difference.) =C2=A0Caused the system to go *really*= slow when > powerd started and decided that since CPU usage was 0.00% it could safely > throttle the CPU all the way down midway thru all the rc.d/* stuff > executing. :-) > > As near as I can tell, the culprit is this rev (and the SVN #s you quote > are consistent with this being the case): > > =C2=A0SVN rev 202387 on 2010-01-15 16:04:30Z by attilio > > =C2=A0Handling all the three clocks (hardclock, softclock, profclock) wit= h the > =C2=A0LAPIC may lead to aliasing for softclock and profclock because freq= uencies > =C2=A0are sized in order to fit mainly hardclock. > =C2=A0atrtc used to take care of the softclock and profclock and it does = still > =C2=A0do, if the LAPIC can't handle the clocks properly. > > =C2=A0Revert the change when the LAPIC started taking charge of all three= of > =C2=A0them and let atrtc handle softclock and profclock if not explicitly > =C2=A0requested. Such request can be made setting !=3D 0 the new tunable > =C2=A0machdep.lapic_allclocks or if the new device ATPIC is not present > =C2=A0within the i386 kernel config (atrtc is linked to atpic presence). > > As a check, my current post-rev-202387 kernel has working clock if I boot= with > > =C2=A0machdep.lapic_allclocks=3D1 Can you all please do: % sysctl kern.timecounter Thanks, Attilio --=20 Peace can only be achieved by understanding - A. Einstein