DMARC-Filter: OpenDMARC Filter v1.3.2 mx1.redhat.com 8C69AC04D2BC
Message-ID: <1491402411.16856.5.camel@redhat.com>
Subject: Re: [BUG nohz]: wrong user and system time accounting
From: Rik van Riel <riel@redhat.com>
To: Luiz Capitulino <lcapitulino@redhat.com>,
        Frederic Weisbecker <fweisbec@gmail.com>
Cc: Wanpeng Li <kernellwp@gmail.com>, Mike Galbraith <efault@gmx.de>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 05 Apr 2017 10:26:51 -0400
In-Reply-To: <20170404133638.178b29f7@redhat.com>
References: <1490818125.28917.11.camel@redhat.com>
         <1490848051.4167.57.camel@gmx.de>
         <CANRm+CzfqkU6iV1BFk3PmWvy7MOsYH1mSwejJXMkvWW9C5ngwg@mail.gmail.com>
         <20170330133802.GC3626@lerouge>
         <CANRm+Cw8-7PydicanPCkNcVLi16Yr_0J9Sj6m6xWp4OUxLywjQ@mail.gmail.com>
         <20170330141816.GE3626@lerouge> <20170330172546.4e8e1a6a@redhat.com>
         <20170331160910.0dda403e@redhat.com> <20170331232452.GA10607@lerouge>
         <20170331231119.2b78eb1f@redhat.com> <20170403152315.GA4221@lerouge>
         <20170403150613.77541109@redhat.com> <20170404133638.178b29f7@redhat.com>
Content-Type: multipart/signed; micalg="pgp-sha256";
        protocol="application/pgp-signature"; boundary="=-UaDY7zjYiai7YIvuEIR5"
Mime-Version: 1.0
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2561
Lines: 68


--=-UaDY7zjYiai7YIvuEIR5
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Tue, 2017-04-04 at 13:36 -0400, Luiz Capitulino wrote:
>=C2=A0
> On further debugging this, I realized that I had overlooked
> something:
> the timer interrupt in this trace is not the tick, but cyclictest's
> timer
> (remember that the test-case consists of pinning cyclictest and a
> task
> hogging the CPU to the same CPU).
>=20
> I'm running cyclictest with -i 200. If I increase this to -i 1000,
> then
> I seem unable to reproduce the issue (caution: even with -i 200 it
> doesn't always happen. But it does usually happen after I restart the
> test-case a few times. However, I've never been able to reproduce
> with -i 1000).
>=20
> Now, if it's really cyclictest that's causing the timer interrupts to
> get aligned, I guess this might not have a solution? (note: I haven't
> been able to reproduce this on bare-metal).

With any sample (tick) based timekeeping, it is possible
to construct workloads that avoid the sampling and result
in skewed statistics as a result.

However, given that local users can already DoS the system
in all kinds of ways, skewed statistics are probably not
that high up on the list of importance.

If there were a way to do accurate accounting (true vtime
accounting) without increasing the overhead of every
syscall and interrupt noticeably, that might be worth it,
but syscall overhead is likely to be a more important
factor than the accuracy of statistics.

I don't know if doing TSC reads and subtraction/addition
only, and delaying the conversion to cputime until a later
point would slow down system calls measurably, compared
with reading jiffies and comparing it against a cached
value of jiffies, nor do I know whether spending time
implementing and testing that would be worthwhile :)

--=20
All rights reversed

--=-UaDY7zjYiai7YIvuEIR5
Content-Type: application/pgp-signature; name="signature.asc"
Content-Description: This is a digitally signed message part
Content-Transfer-Encoding: 7bit

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2

iQEcBAABCAAGBQJY5P6rAAoJEM553pKExN6DfNkH/AzccvzSHlOozVU9BNNMVPqb
Cex04shUpnP8XFMEc03jHMNZdkpP3U4eUEYKu7RzU+pP4tql1ngvyhOvFja4zp5W
Mk1yWyVy81yaZHaDml1E6dIfBdwRAhh1JX1/RbDr6Of2KtA7fws0Dyoh+RhVM5ms
Aqy4R/n+VKJaChTmCGWDsbWhdkFcfZ+HGfTEXZQvSi/9iKxfGsYH4U4t3tcVfi7B
FV9afmet2CdZuruvbC6wBBcGzaD80nhhJIhW+7IfmJvRHIjzV9LLGXlVSUbwkELb
lFTZaJV9hNCWicpvT6uYoMRWOu9Y/SW4J4nGCYdw2MwqBPMPaYQWLmY61LJcD18=
=kQv5
-----END PGP SIGNATURE-----

--=-UaDY7zjYiai7YIvuEIR5--