From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933893Ab1CaO7x (ORCPT ); Thu, 31 Mar 2011 10:59:53 -0400 Received: from mx1.redhat.com ([209.132.183.28]:60610 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933166Ab1CaO7v (ORCPT ); Thu, 31 Mar 2011 10:59:51 -0400 Date: Thu, 31 Mar 2011 10:58:50 -0400 From: Dave Jones To: Linus Torvalds Cc: Andrew Morton , Linux Kernel , Tejun Heo Subject: Re: excessive kworker activity when idle. (was Re: vma corruption in today's -git) Message-ID: <20110331145850.GA10163@redhat.com> Mail-Followup-To: Dave Jones , Linus Torvalds , Andrew Morton , Linux Kernel , Tejun Heo References: <20110329040939.GA32764@redhat.com> <20110331030917.GB26057@redhat.com> <20110331035511.GA1255@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, Mar 30, 2011 at 10:32:11PM -0700, Linus Torvalds wrote: > On Wed, Mar 30, 2011 at 8:55 PM, Dave Jones wrote: > > > > I tried that, and wasn't particularly enlightened. > > > > +      6.53%  kworker/1:2  [kernel.kallsyms]  [k] read_hpet > > +      4.83%  kworker/0:0  [kernel.kallsyms]  [k] read_hpet > > Go into those, deeper into the callchain. That's how to see what the > upper-level problem is - by seeing who actually calls it. The leafs > themselves (where the time is obviously spent) don't tend to be very > informative, no. ok, a bit more interesting ? - 17.67% kworker/0:1 [kernel.kallsyms] [k] read_hpet - read_hpet - 76.07% timekeeping_get_ns - ktime_get - 64.02% tick_dev_program_event tick_program_event hrtimer_interrupt smp_apic_timer_interrupt + apic_timer_interrupt - 35.30% sched_clock_tick scheduler_tick update_process_times tick_sched_timer __run_hrtimer hrtimer_interrupt smp_apic_timer_interrupt - apic_timer_interrupt + 65.70% _raw_spin_unlock_irqrestore + 27.33% _raw_spin_unlock_irq + 1.16% lock_acquire + 1.16% put_ldisc + 1.16% process_one_work + 1.16% lock_release + 0.78% worker_thread + 0.58% _raw_spin_lock_irqsave + 0.55% tick_sched_timer - 23.82% do_timer tick_do_update_jiffies64 tick_sched_timer __run_hrtimer hrtimer_interrupt smp_apic_timer_interrupt - apic_timer_interrupt + 63.46% _raw_spin_unlock_irqrestore + 22.98% _raw_spin_unlock_irq + 3.50% put_ldisc + 3.28% lock_acquire btw, I left this on overnight capturing the output of /proc/loadavg it didn't drop off at all, and this morning the laptop is almost too hot to hold. Dave