Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758166Ab0FORZp (ORCPT ); Tue, 15 Jun 2010 13:25:45 -0400 Received: from mail-vw0-f46.google.com ([209.85.212.46]:48667 "EHLO mail-vw0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758099Ab0FORZo convert rfc822-to-8bit (ORCPT ); Tue, 15 Jun 2010 13:25:44 -0400 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:content-type :content-transfer-encoding; b=HqU3Gn3JFfqu20r6OwELn8TouV3MtheYSolyPj9slhPAvN+MoXj8EUY/ikTokw8fyT wr87c1uE+etCjMeIgvGR14fGw71blBdvTw37RhxHBmk1LN1If1AxG4e27AEQS2HKUFMq hP+12SSe4ZPY7ei09kyGw/KMxu8BZoV9MwQQE= MIME-Version: 1.0 In-Reply-To: <20100614214646.GF6666@thunk.org> References: <20100613194949.GC8055@thunk.org> <20100614184244.GA11480@elliptictech.com> <20100614214646.GF6666@thunk.org> Date: Tue, 15 Jun 2010 18:25:42 +0100 X-Google-Sender-Auth: PbHSKff5OIaKM8LAaVtT_C6Nbzg Message-ID: Subject: Re: Why is kslowd accumulating so much CPU time? From: Andy Whitcroft To: tytso@mit.edu, Dave Airlie , Dave Airlie , David Howells , linux-kernel@vger.kernel.org Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2169 Lines: 41 On Mon, Jun 14, 2010 at 10:46 PM, wrote: > On Mon, Jun 14, 2010 at 02:42:44PM -0400, Nick Bowler wrote: >> >> This sounds exactly like the issue I've been seeing on a T500 laptop, as >> well (GM45 board). ?The slowdowns render the system essentially >> unusable, as it can spend a loooong time just moving the mouse cursor a >> few pixels on the screen. ?During this time, nothing else on the display >> is updating (glxgears drops to 0fps). ?Things generally seem to be >> working fine if I am not moving the mouse, or if I'm not running X. > > I saw exactly the same behaviour when using the Ubuntu Karmic > userspace. ?Basically, using a 2.6.35-rc2 (+ vt memory corrupter fix) > kernel, the system was essentially unusable. ?Interestingly, the > problem went away (with the same kernel) once I updated to Ubuntu > Lucid. ?I was going to mention that so that hopefully someone with far > more X.org-fu than I could figure out how much of this is a X server > bug, and how much of this was a kernel bug, but things worked just > *fine* with 2.6.34 kernel. > > Occasionally it will happen that the mouse stops tracking, and then I > grumble and curse, and a few seconds later it resolves itself. ?I > haven't had time to track it down; but the problem was breathtakingly > easy to reproduce with an Ubuntu Karmic userspace. ?:-) I am seeing crunchy cursor behavior on boot on Ubuntu Lucid user space with the 2.6.35-rc3 kernel as well. It pretty much always does that on boot, and often later as well. Right now I have four of these chaps each consuming 9% of a CPU. Though they definatly come and go. Very odd: 938 root 15 -5 0 0 0 S 9 0.0 1:00.90 kslowd001 1048 root 15 -5 0 0 0 S 9 0.0 1:01.12 kslowd002 937 root 15 -5 0 0 0 S 8 0.0 1:00.92 kslowd000 1544 root 15 -5 0 0 0 D 8 0.0 1:00.55 kslowd003 -apw -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/