From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752987AbaHDOb2 (ORCPT ); Mon, 4 Aug 2014 10:31:28 -0400 Received: from mx1.redhat.com ([209.132.183.28]:27033 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752960AbaHDOb0 (ORCPT ); Mon, 4 Aug 2014 10:31:26 -0400 Date: Mon, 4 Aug 2014 10:31:22 -0400 From: Don Zickus To: chai wen Cc: linux-kernel@vger.kernel.org, mingo@redhat.com Subject: Re: [PATCH 2/2] softlockup: make detector be aware of task switch of processes hogging cpu Message-ID: <20140804143122.GF87407@redhat.com> References: <1407137779-19129-1-git-send-email-chaiw.fnst@cn.fujitsu.com> <1407137779-19129-2-git-send-email-chaiw.fnst@cn.fujitsu.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1407137779-19129-2-git-send-email-chaiw.fnst@cn.fujitsu.com> 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 Mon, Aug 04, 2014 at 03:36:19PM +0800, chai wen wrote: > > For now, soft lockup detector warns once for each case of process softlockup. > But the thread 'watchdog/n' may can not always get cpu at the time slot between > the task switch of two processes hogging that cpu. > This case is a false negative of "warn only once for a process", as there may be > a different process that is going to hog the cpu. Is is better for detector to > be aware of it. I am not sure I fully understand the problem resolved. >>From the changelog I understood that two processes bouncing back and forth could hog the cpu and could create a 'false negative' (a situation not reported but should). But looking at the patch below I was a little confused on the __touch_watchdog addition. See below: > > Signed-off-by: chai wen > --- > kernel/watchdog.c | 18 ++++++++++++++++-- > 1 files changed, 16 insertions(+), 2 deletions(-) > > diff --git a/kernel/watchdog.c b/kernel/watchdog.c > index 4c2e11c..908050c 100644 > --- a/kernel/watchdog.c > +++ b/kernel/watchdog.c > @@ -42,6 +42,7 @@ static DEFINE_PER_CPU(bool, softlockup_touch_sync); > static DEFINE_PER_CPU(bool, soft_watchdog_warn); > static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); > static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); > +static DEFINE_PER_CPU(pid_t, softlockup_warn_pid_saved); > #ifdef CONFIG_HARDLOCKUP_DETECTOR > static DEFINE_PER_CPU(bool, hard_watchdog_warn); > static DEFINE_PER_CPU(bool, watchdog_nmi_touch); > @@ -317,6 +318,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) > */ > duration = is_softlockup(touch_ts); > if (unlikely(duration)) { > + pid_t pid = task_pid_nr(current); > + > /* > * If a virtual machine is stopped by the host it can look to > * the watchdog like a soft lockup, check to see if the host > @@ -326,8 +329,18 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) > return HRTIMER_RESTART; > > /* only warn once */ > - if (__this_cpu_read(soft_watchdog_warn) == true) > + if (__this_cpu_read(soft_watchdog_warn) == true) { > + /* > + * soft lockup detector should be aware of that there > + * may be a task-swicth of two different processes > + * hogging the cpu continously > + */ > + if (__this_cpu_read(softlockup_warn_pid_saved) != pid) { > + __this_cpu_write(soft_watchdog_warn, false); > + __touch_watchdog(); > + } The above piece is what I am trying to understand. Are you saying that when two different processes are hogging the cpu, undo the soft_watchdog_warn and allow the second pid to be reported? Just trying to understand the problem and see if this is the right approach (because 3 or more processes could cause the same problem???). Cheers, Don > return HRTIMER_RESTART; > + } > > if (softlockup_all_cpu_backtrace) { > /* Prevent multiple soft-lockup reports if one cpu is already > @@ -342,7 +355,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) > > printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", > smp_processor_id(), duration, > - current->comm, task_pid_nr(current)); > + current->comm, pid); > + __this_cpu_write(softlockup_warn_pid_saved, pid); > print_modules(); > print_irqtrace_events(current); > if (regs) > -- > 1.7.1 >