Re: [PATCH v2] sched/cputime: add steal clock warp handling

Path	csiph.com!eternal-september.org!feeder.eternal-september.org!aioe.org!bofh.it!news.nic.it!robomod
From	Rik van Riel <riel@redhat.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH v2] sched/cputime: add steal clock warp handling
Date	Fri, 03 Jun 2016 15:20:02 +0200
Message-ID	<rFXb4-3BY-13@gated-at.bofh.it> (permalink)
References	<rFPQd-7wo-7@gated-at.bofh.it>
Content-Type	multipart/signed; micalg="pgp-sha256"; protocol="application/pgp-signature"; boundary="=-Wzt6W+CLFflvDd4OdRW7"
MIME-Version	1.0
X-Scanned-By	MIMEDefang 2.68 on 10.5.11.27
X-Greylist	Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.25]); Fri, 03 Jun 2016 13:10:15 +0000 (UTC)
Sender	robomod@news.nic.it
List-ID	<linux-kernel.vger.kernel.org>
X-Mailing-List	linux-kernel@vger.kernel.org
Approved	robomod@news.nic.it
Lines	81
Organization	linux.* mail to news gateway
X-Original-Cc	Wanpeng Li <wanpeng.li@hotmail.com>, Ingo Molnar <mingo@kernel.org>, "Peter Zijlstra (Intel)" <peterz@infradead.org>, Thomas Gleixner <tglx@linutronix.de>, Frederic Weisbecker <fweisbec@gmail.com>, Paolo Bonzini <pbonzini@redhat.com>, Radim <rkrcmar@redhat.com>
X-Original-Date	Fri, 03 Jun 2016 09:10:07 -0400
X-Original-Message-ID	<1464959407.16365.120.camel@redhat.com>
X-Original-References	<1464931288-5886-1-git-send-email-wanpeng.li@hotmail.com>
X-Original-Sender	linux-kernel-owner@vger.kernel.org
Xref	csiph.com linux.kernel:1413229

Show key headers only | View raw

[Multipart message — attachments visible in raw view] - view raw

On Fri, 2016-06-03 at 13:21 +0800, Wanpeng Li wrote:
> From: Wanpeng Li <wanpeng.li@hotmail.com>
> 
> I observed that sometimes st is 100% instantaneous, then idle is
> 100% 
> even if there is a cpu hog on the guest cpu after the cpu hotplug
> comes 
> back(N.B. this can not always be readily reproduced). I add trace to 
> capture it as below:
> 
> cpuhp/1-12    [001] d.h1   167.461657: account_process_tick: steal =
> 1291385514, prev_steal_time = 0         
> cpuhp/1-12    [001] d.h1   167.461659: account_process_tick:
> steal_jiffies = 1291          
> <idle>-0     [001] d.h1   167.462663: account_process_tick: steal =
> 18732255, prev_steal_time = 1291000000          
> <idle>-0     [001] d.h1   167.462664: account_process_tick:
> steal_jiffies = 18446744072437
> 
> The steal clock warp and then steal_jiffies overflow.
> 
> Rik also pointed out to me:
>  
> > 
> > I have seen stuff like that with live migration too, in the past 
> This patch adds steal clock warp handling by a safe threshold to
> only 
> apply steal times that are positive and smaller than one second (as 
> long as nohz_full has the one second timer tick left), ignoring
> intervals 
> that are negative or longer than a second, and using those to sync
> up 
> the guest with the host.
> 
> Cc: Ingo Molnar <mingo@kernel.org>
> Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
> Cc: Rik van Riel <riel@redhat.com>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Frederic Weisbecker <fweisbec@gmail.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Radim <rkrcmar@redhat.com>
> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
> 

Reviewed-by: Rik van Riel <riel@redhat.com>

-- 
All Rights Reversed.

Thread

[PATCH v2] sched/cputime: add steal clock warp handling Wanpeng Li <kernellwp@gmail.com> - 2016-06-03 07:30 +0200
  Re: [PATCH v2] sched/cputime: add steal clock warp handling Rik van Riel <riel@redhat.com> - 2016-06-03 15:20 +0200
    Re: [PATCH v2] sched/cputime: add steal clock warp handling Paolo Bonzini <pbonzini@redhat.com> - 2016-06-06 15:50 +0200
      Re: [PATCH v2] sched/cputime: add steal clock warp handling Rik van Riel <riel@redhat.com> - 2016-06-06 16:30 +0200
        Re: [PATCH v2] sched/cputime: add steal clock warp handling Paolo Bonzini <pbonzini@redhat.com> - 2016-06-06 16:40 +0200

csiph-web