Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756834Ab0FNVqv (ORCPT ); Mon, 14 Jun 2010 17:46:51 -0400 Received: from THUNK.ORG ([69.25.196.29]:51920 "EHLO thunker.thunk.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755295Ab0FNVqt (ORCPT ); Mon, 14 Jun 2010 17:46:49 -0400 Date: Mon, 14 Jun 2010 17:46:46 -0400 From: tytso@mit.edu To: Dave Airlie , Dave Airlie , David Howells , linux-kernel@vger.kernel.org Subject: Re: Why is kslowd accumulating so much CPU time? Message-ID: <20100614214646.GF6666@thunk.org> Mail-Followup-To: tytso@mit.edu, Dave Airlie , Dave Airlie , David Howells , linux-kernel@vger.kernel.org References: <20100613194949.GC8055@thunk.org> <20100614184244.GA11480@elliptictech.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100614184244.GA11480@elliptictech.com> User-Agent: Mutt/1.5.20 (2009-06-14) X-SA-Exim-Connect-IP: X-SA-Exim-Mail-From: tytso@thunk.org X-SA-Exim-Scanned: No (on thunker.thunk.org); SAEximRunCond expanded to false Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1531 Lines: 29 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. :-) - Ted -- 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/