Re: utime accounting regression since 4.6 (was: Re: [PACTH v2 0/3] Implement /proc/<pid>/totmaps)

From: Rik van Riel <riel@redhat.com>
To: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>,
	Sonny Rao <sonnyrao@chromium.org>, Jann Horn <jann@thejh.net>,
	Robert Foss <robert.foss@collabora.com>,
	corbet@lwn.net, Andrew Morton <akpm@linux-foundation.org>,
	Vlastimil Babka <vbabka@suse.cz>,
	Konstantin Khlebnikov <koct9i@gmail.com>,
	Hugh Dickins <hughd@google.com>,
	Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>,
	John Stultz <john.stultz@linaro.org>,
	ross.zwisler@linux.intel.com, jmarchan@redhat.com,
	Johannes Weiner <hannes@cmpxchg.org>,
	Kees Cook <keescook@chromium.org>,
	Al Viro <viro@zeniv.linux.org.uk>,
	Cyrill Gorcunov <gorcunov@openvz.org>,
	Robin Humble <plaguedbypenguins@gmail.com>,
	David Rientjes <rientjes@google.com>,
	eric.engestrom@imgtec.com, Janis Danisevskis <jdanis@google.com>,
	calvinowens@fb.com, Alexey Dobriyan <adobriyan@gmail.com>,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	ldufour@linux.vnet.ibm.com, linux-doc@vger.kernel.org,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Ben Zhang <benzh@chromium.org>, Bryan Freed <bfreed@chromium.org>,
	Filipe Brandenburger <filbranden@chromium.org>,
	Mateusz Guzik <mguzik@redhat.com>, Mel Gorman <mgorman@suse.de>,
	Mike Galbraith <mgalbraith@suse.com>
Subject: Re: utime accounting regression since 4.6 (was: Re: [PACTH v2 0/3] Implement /proc/<pid>/totmaps)
Date: Fri, 30 Sep 2016 08:35:50 -0400	[thread overview]
Message-ID: <1475238950.19362.3.camel@redhat.com> (raw)
In-Reply-To: <20160930094905.GA22867@dhcp22.suse.cz>

[-- Attachment #1: Type: text/plain, Size: 1192 bytes --]

On Fri, 2016-09-30 at 11:49 +0200, Michal Hocko wrote:
> [CC Mike and Mel as they have seen some accounting oddities
>  when doing performance testing. They can share details but
>  essentially the system time just gets too high]
> 
> For your reference the email thread started
> http://lkml.kernel.org/r/20160823143330.GL23577@dhcp22.suse.cz
> 
> I suspect this is mainly for short lived processes - like kernel
> compile
> $ /usr/bin/time -v make mm/mmap.o
> [...]
>         User time (seconds): 0.45
>         System time (seconds): 0.82
>         Percent of CPU this job got: 111%
>         Elapsed (wall clock) time (h:mm:ss or m:ss): 0:01.14
> $ rm mm/mmap.o
> $ /usr/bin/time -v make mm/mmap.o
> [...]
>         User time (seconds): 0.47
>         System time (seconds): 1.55
>         Percent of CPU this job got: 107%
>         Elapsed (wall clock) time (h:mm:ss or m:ss): 0:01.88

I was not able to get the "expected" results from
your last reproducer, but this one does happen on
my system, too.

The bad news is, I still have no clue what is causing
it...

-- 
All Rights Reversed.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 473 bytes --]