From: Frederic Weisbecker <fweisbec@gmail.com>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <kernellwp@gmail.com>, Mike Galbraith <efault@gmx.de>,
Rik van Riel <riel@redhat.com>,
Luiz Capitulino <lcapitulino@redhat.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Peter Zijlstra <peterz@infradead.org>
Subject: Re: [BUG nohz]: wrong user and system time accounting
Date: Wed, 12 Apr 2017 15:18:19 +0200 [thread overview]
Message-ID: <20170412131818.GB21309@lerouge> (raw)
In-Reply-To: <alpine.DEB.2.20.1704111523100.1772@nanos>
On Tue, Apr 11, 2017 at 04:22:48PM +0200, Thomas Gleixner wrote:
> On Thu, 30 Mar 2017, Wanpeng Li wrote:
> > diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
> > index f3778e2b..f1ee393 100644
> > --- a/kernel/sched/cputime.c
> > +++ b/kernel/sched/cputime.c
> > @@ -676,18 +676,21 @@ void thread_group_cputime_adjusted(struct
> > task_struct *p, u64 *ut, u64 *st)
> > #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
> > static u64 vtime_delta(struct task_struct *tsk)
> > {
> > - unsigned long now = READ_ONCE(jiffies);
> > + u64 now = local_clock();
> > + u64 delta;
> > +
> > + delta = now - tsk->vtime_snap;
> >
> > - if (time_before(now, (unsigned long)tsk->vtime_snap))
> > + if (delta < TICK_NSEC)
> > return 0;
> >
> > - return jiffies_to_nsecs(now - tsk->vtime_snap);
> > + return jiffies_to_nsecs(delta / TICK_NSEC);
>
> So you replaced a jiffies based approach with a jiffies based approach.
>
> > }
> >
> > static u64 get_vtime_delta(struct task_struct *tsk)
> > {
> > - unsigned long now = READ_ONCE(jiffies);
> > - u64 delta, other;
> > + u64 delta = vtime_delta(tsk);
> > + u64 other;
> >
> > /*
> > * Unlike tick based timing, vtime based timing never has lost
> > @@ -696,10 +699,9 @@ static u64 get_vtime_delta(struct task_struct *tsk)
> > * elapsed time. Limit account_other_time to prevent rounding
> > * errors from causing elapsed vtime to go negative.
> > */
> > - delta = jiffies_to_nsecs(now - tsk->vtime_snap);
> > other = account_other_time(delta);
> > WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
> > - tsk->vtime_snap = now;
> > + tsk->vtime_snap += delta;
>
> Here is how it works^Wfails
>
> For simplicity tsk->vtime_snap starts at 0
> HZ = 1000
>
> CPU0 CPU1
> sysexit()
> account_system()
> now == 0
> delta = vtime_delta() <- 0ns
> tsk->vtime_snap += delta; == 0ns
>
> busy_loop(995us)
>
> sysenter()
> now == 996us
> account_user()
> delta = vtime_delta() <- 0ns
> tsk->vtime_snap += delta == 0ns
>
> sysexit()
> account_system()
> now == 1001us
> delta = vtime_delta() <- 10000000ns
>
> ^^^^ Gets accounted to system
>
> tsk->vtime_snap += delta; == 10000000ns
>
> It's not different from the current jiffies based stuff at all. Same
> failure mode.
Yes you're right, I got confused again. So to fix this we could do our snapshots
at a frequency lower than HZ but still high enough to avoid overhead.
Something like TICK_NSEC / 2 ?
next prev parent reply other threads:[~2017-04-12 13:18 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-23 20:55 [BUG nohz]: wrong user and system time accounting Luiz Capitulino
2017-03-24 0:56 ` Rik van Riel
2017-03-24 1:05 ` Luiz Capitulino
2017-03-24 1:08 ` Rik van Riel
2017-03-24 1:39 ` Luiz Capitulino
2017-03-27 5:33 ` lkml
2017-03-24 1:52 ` Wanpeng Li
2017-03-24 3:56 ` Luiz Capitulino
2017-03-27 1:56 ` Wanpeng Li
2017-03-27 17:35 ` Rik van Riel
2017-03-28 7:19 ` Wanpeng Li
[not found] ` <20170328132406.7d23579c@redhat.com>
[not found] ` <20170328161454.4a5d9e8b@redhat.com>
2017-03-28 21:01 ` Rik van Riel
2017-03-28 21:26 ` Luiz Capitulino
2017-03-29 9:56 ` Wanpeng Li
2017-03-29 12:56 ` Frederic Weisbecker
2017-03-28 21:24 ` Rik van Riel
2017-03-28 21:30 ` Luiz Capitulino
[not found] ` <20170329131656.1d6cb743@redhat.com>
2017-03-29 20:08 ` Rik van Riel
2017-03-29 22:54 ` Frederic Weisbecker
2017-03-30 12:57 ` Rik van Riel
2017-03-30 1:58 ` Wanpeng Li
2017-03-30 12:40 ` Frederic Weisbecker
2017-03-30 13:19 ` Mike Galbraith
2017-03-30 4:27 ` Mike Galbraith
2017-03-30 6:47 ` Wanpeng Li
2017-03-30 11:52 ` Wanpeng Li
2017-03-30 12:33 ` Mike Galbraith
2017-03-30 13:38 ` Frederic Weisbecker
2017-03-30 13:59 ` Wanpeng Li
2017-03-30 14:18 ` Frederic Weisbecker
2017-03-30 21:25 ` Luiz Capitulino
2017-03-31 20:09 ` Luiz Capitulino
2017-03-31 23:24 ` Frederic Weisbecker
2017-04-01 3:11 ` Luiz Capitulino
2017-04-03 15:23 ` Frederic Weisbecker
2017-04-03 19:06 ` Luiz Capitulino
2017-04-04 17:36 ` Luiz Capitulino
2017-04-05 14:26 ` Rik van Riel
2017-04-11 11:03 ` Wanpeng Li
2017-04-11 11:36 ` Peter Zijlstra
2017-04-11 11:43 ` Wanpeng Li
2017-04-11 14:22 ` Thomas Gleixner
2017-04-12 13:18 ` Frederic Weisbecker [this message]
2017-04-12 14:57 ` Thomas Gleixner
2017-04-12 15:14 ` Frederic Weisbecker
2017-04-13 4:31 ` Wanpeng Li
2017-04-13 13:32 ` Frederic Weisbecker
2017-05-02 10:01 ` Wanpeng Li
2017-05-15 8:17 ` Wanpeng Li
2017-06-29 17:22 ` Frederic Weisbecker
2017-03-30 12:51 ` Frederic Weisbecker
2017-03-30 13:02 ` Rik van Riel
2017-03-30 13:35 ` Mike Galbraith
2017-04-03 14:40 ` Frederic Weisbecker
2017-04-04 7:32 ` Mike Galbraith
2017-03-30 13:44 ` Frederic Weisbecker
[not found] ` <20170329221700.GB23895@lerouge>
2017-03-29 22:46 ` Wanpeng Li
2017-03-30 2:14 ` Luiz Capitulino
2017-03-30 12:27 ` Wanpeng Li
2017-03-27 18:38 ` Luiz Capitulino
2017-03-28 5:28 ` Wanpeng Li
2017-03-28 13:44 ` Luiz Capitulino
2017-03-29 13:04 ` Frederic Weisbecker
2017-03-29 13:14 ` Rik van Riel
2017-03-29 13:23 ` Luiz Capitulino
2017-03-29 21:12 ` Frederic Weisbecker
2017-03-30 1:48 ` Luiz Capitulino
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170412131818.GB21309@lerouge \
--to=fweisbec@gmail.com \
--cc=efault@gmx.de \
--cc=kernellwp@gmail.com \
--cc=lcapitulino@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=riel@redhat.com \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).