From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757299AbXITQTT (ORCPT ); Thu, 20 Sep 2007 12:19:19 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756753AbXITQTL (ORCPT ); Thu, 20 Sep 2007 12:19:11 -0400 Received: from mx1.redhat.com ([66.187.233.31]:45009 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756213AbXITQTK (ORCPT ); Thu, 20 Sep 2007 12:19:10 -0400 Message-ID: <46F29D7A.9070309@redhat.com> Date: Thu, 20 Sep 2007 12:19:06 -0400 From: Chuck Ebbert Organization: Red Hat User-Agent: Thunderbird 1.5.0.12 (X11/20070719) MIME-Version: 1.0 To: Aggelos Manousarides CC: linux-kernel@vger.kernel.org Subject: Re: Bogus high interrupt load? References: <20070918235648.GA29746@inaccessnetworks.com> In-Reply-To: <20070918235648.GA29746@inaccessnetworks.com> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On 09/18/2007 07:56 PM, Aggelos Manousarides wrote: > > There is obviously something happening to the load reporting facility of > the kernel when a periodic interrupt source is present. Has anyone seen > something like this? I am not using any real time patches, this is a > vanilla kernel patched only to support the platform at hand. > You will get aliasing effects like that if the system clock is not interrupting at least twice as often as your periodic interrupts occur.