Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752697AbYKQPhn (ORCPT ); Mon, 17 Nov 2008 10:37:43 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751745AbYKQPhe (ORCPT ); Mon, 17 Nov 2008 10:37:34 -0500 Received: from zrtps0kp.nortel.com ([47.140.192.56]:62575 "EHLO zrtps0kp.nortel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750919AbYKQPhd (ORCPT ); Mon, 17 Nov 2008 10:37:33 -0500 Message-ID: <49218FB4.6090805@nortel.com> Date: Mon, 17 Nov 2008 09:37:24 -0600 From: "Chris Friesen" User-Agent: Thunderbird 2.0.0.17 (X11/20080914) MIME-Version: 1.0 To: Ken Chen CC: Ingo Molnar , Peter Zijlstra , Linux Kernel Mailing List Subject: Re: busted CFS group load balancer? References: <20081115011452.GA28135@google.com> In-Reply-To: <20081115011452.GA28135@google.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-OriginalArrivalTime: 17 Nov 2008 15:37:25.0700 (UTC) FILETIME=[641D3840:01C948CA] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 719 Lines: 18 Ken Chen wrote: > It appears that the fair-group load balancer in 2.6.27 does not work > properly. There was an issue fixed post 2.6.27 where the load balancer didn't work properly if there was one task per group per cpu. You might try backporting commit 38736f4 and see if that helps. Also, caea8a0 fixes up list traversal in load_balance_fair() to use the _rcu() version. I'm not aware of this causing any problems in practice, but it might be worth a try. Chris -- 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/