From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756446Ab0IHWZa (ORCPT ); Wed, 8 Sep 2010 18:25:30 -0400 Received: from icebox.esperi.org.uk ([81.187.191.129]:51330 "EHLO mail.esperi.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756281Ab0IHWZZ (ORCPT ); Wed, 8 Sep 2010 18:25:25 -0400 To: John Drescher Cc: Damien Wyart , linux-kernel@vger.kernel.org Subject: Re: 2.6.35.*: horrible (exponential? >linear) slowdown to unusability (ACPI idle?) References: <87zkvx2ese.fsf@spindle.srvr.nix> <20100906053255.GA23340@brouette> <87iq2gyllg.fsf@spindle.srvr.nix> From: Nix Emacs: Our Lady of Perpetual Garbage Collection Date: Wed, 08 Sep 2010 23:25:22 +0100 In-Reply-To: (John Drescher's message of "Wed, 8 Sep 2010 17:35:48 -0400") Message-ID: <87eid3zxd9.fsf@spindle.srvr.nix> User-Agent: Gnus/5.1008 (Gnus v5.10.8) XEmacs/21.5-b29 (linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-DCC-z.dcc-servers-Metrics: spindle 1049; Body=3 Fuz1=3 Fuz2=3 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 8 Sep 2010, John Drescher spake thusly: > I believe I have the same problem reported in your first post. Or at > least a lot of the symptoms. > > http://forums.gentoo.org/viewtopic-t-842775-postdays-0-postorder-asc-start-0.html Yeah, that looks mostly the same, though when I see it with CONFIG_NO_HZ, I get an increasing slowdown to unusability, not instant sloth as you do. (The WD GreenPower thing is a complete red herring, of course: if that was the cause of the sloth, it would be slow in other kernels too. I see this both on machines with -- non-buggy -- GreenPowers behind an Areca RAID array, and on machines with totally different brands of drives. ToI is likewise a complete red herring.)