From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1030299AbXBGWxH (ORCPT ); Wed, 7 Feb 2007 17:53:07 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1422807AbXBGWxH (ORCPT ); Wed, 7 Feb 2007 17:53:07 -0500 Received: from mga06.intel.com ([134.134.136.21]:6588 "EHLO orsmga101.jf.intel.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1030299AbXBGWxE (ORCPT ); Wed, 7 Feb 2007 17:53:04 -0500 X-ExtLoop1: 1 X-IronPort-AV: i="4.13,297,1167638400"; d="scan'208"; a="194117277:sNHT110345767" Date: Wed, 7 Feb 2007 14:19:19 -0800 From: "Siddha, Suresh B" To: mingo@elte.hu Cc: Ingo Molnar , vatsa@in.ibm.com, clameter@sgi.com, tglx@linutronix.de, arjan@linux.intel.com, linux-kernel@vger.kernel.org Subject: Re: [RFC] Patch: dynticks: idle load balancing Message-ID: <20070207141919.C19581@unix-os.sc.intel.com> References: <20061211155304.A31760@unix-os.sc.intel.com> <20061213224317.GA2986@elte.hu> <20061213231316.GA13849@elte.hu> <20061213150314.B12795@unix-os.sc.intel.com> <20061213233157.GA20470@elte.hu> <20061213151926.C12795@unix-os.sc.intel.com> <20061219201247.GA12648@elte.hu> <20061219131223.E23105@unix-os.sc.intel.com> <20070116113505.GA6294@elte.hu> <20070130135709.B32010@unix-os.sc.intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline User-Agent: Mutt/1.2.5.1i In-Reply-To: <20070130135709.B32010@unix-os.sc.intel.com>; from suresh.b.siddha@intel.com on Tue, Jan 30, 2007 at 01:57:09PM -0800 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Jan 30, 2007 at 01:57:09PM -0800, Siddha, Suresh B wrote: > Please let me know if you still see this issue with the latest -rt kernel. > > On Tue, Jan 16, 2007 at 12:35:05PM +0100, Ingo Molnar wrote: > > on the latest -rt kernel, when the dynticks load-balancer is enabled, > > then a dual-core Core2 Duo test-system increases its irq rate from the > > normal 15/17 per second to 300-400/sec - on a completely idle system(!). > > Any idea what's going on? I'll disable the load balancer for now. Ok. got time to look into this. The answer is simple. load_balancing in the recent kernels is happening using SCHED_SOFTIRQ and in -rt tree that happens not in the idle process context but in the context of softirqd for SCHED_SOFTIRQ. This breaks the dynticks load balancer and also the regular idle load balancing too :( Am on to fixing the problem now :) thanks, suresh