public inbox for stable@vger.kernel.org
 help / color / mirror / Atom feed
From: Ivan Delalande <colona@arista.com>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	Rabin Vincent <rabin.vincent@axis.com>,
	Edward Chron <echron@arista.com>,
	stable@vger.kernel.org
Subject: Re: [PATCH 4.9 0/4] Fix softirq time accounting issues on 4.9
Date: Thu, 13 Sep 2018 16:13:17 -0700	[thread overview]
Message-ID: <20180913231317.GB11928@visor> (raw)
In-Reply-To: <20180907014218.18683-1-colona@arista.com>

Hey Greg,

Did you get a chance to look at this series? Thanks a lot!

On Thu, Sep 06, 2018 at 06:42:14PM -0700, Ivan Delalande wrote:
> This series fixes issues we've seen with softirq time accounting in 4.9:
>   - when ksoftirqd is running at 100% on a CPU, none of the values
>     reported by /proc/stat for that CPU will change, sometimes for
>     dozens of seconds,
>   - large deviations in the total number of ticks accumulated over a
>     fixed time for a CPU, probably because of the first issue hitting
>     for shorter periods.
> 
> We found out that something pretty similar had been reported 9 months
> ago, see the reference link below. In that discussion, Rabin Vincent had
> made a 4.9 specific patch which fixes our first issue, but we were still
> seeing some deviation from the total number of ticks (up to 1.7% from
> expected, where we had only 0.2% on older kernels), and you had also
> asked for a direct backport from the mainline series, if possible.
> 
> As mentioned in that thread, a lot of changes (probably 50+) went into
> 4.11 to remove cputime, but we could get something working with only the
> 4 attached patches to fix these two issues. Three of these patches apply
> without change, and the second one in the series ("sched/cputime:
> Convert kcpustat to nsecs") needed a minor change as a cast had been
> added in 527b0a76f41d ("sched/cpuacct: Avoid %lld seq_printf warning")
> to fix a build warning on s390. I guess we could also include that patch
> in this series, let me know if this is the preferred way to handle this.
> 
> We ran our tests on 3.18, 4.4 and 4.9 and confirmed that only 4.9 would
> need this series, and that this series indeed restores the behavior we
> were seeing on those older kernels.
> 
> Thanks!
> 
> Reference: http://lkml.kernel.org/r/%3C1513159876-5125-1-git-send-email-rabin.vincent@axis.com
> 
> 
> Frederic Weisbecker (4):
>   time: Introduce jiffies64_to_nsecs()
>   sched/cputime: Convert kcpustat to nsecs
>   sched/cputime: Increment kcpustat directly on irqtime account
>   sched/cputime: Fix ksoftirqd cputime accounting regression
> 
>  arch/s390/appldata/appldata_os.c   | 16 +++----
>  drivers/cpufreq/cpufreq.c          |  6 +--
>  drivers/cpufreq/cpufreq_governor.c |  2 +-
>  drivers/cpufreq/cpufreq_stats.c    |  1 -
>  drivers/macintosh/rack-meter.c     |  2 +-
>  fs/proc/stat.c                     | 68 +++++++++++++--------------
>  fs/proc/uptime.c                   |  7 +--
>  include/linux/jiffies.h            |  2 +
>  kernel/sched/cpuacct.c             |  2 +-
>  kernel/sched/cputime.c             | 75 +++++++++++++-----------------
>  kernel/sched/sched.h               | 12 +++--
>  kernel/time/time.c                 | 10 ++++
>  kernel/time/timeconst.bc           |  6 +++
>  13 files changed, 109 insertions(+), 100 deletions(-)

-- 
Ivan Delalande
Arista Networks

  parent reply	other threads:[~2018-09-14  4:24 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-07  1:42 [PATCH 4.9 0/4] Fix softirq time accounting issues on 4.9 Ivan Delalande
2018-09-07  1:42 ` [PATCH 4.9 1/4] time: Introduce jiffies64_to_nsecs() Ivan Delalande
2018-09-07  1:42 ` [PATCH 4.9 2/4] sched/cputime: Convert kcpustat to nsecs Ivan Delalande
2018-10-12 14:42   ` Greg Kroah-Hartman
2018-09-07  1:42 ` [PATCH 4.9 3/4] sched/cputime: Increment kcpustat directly on irqtime account Ivan Delalande
2018-09-07  1:42 ` [PATCH 4.9 4/4] sched/cputime: Fix ksoftirqd cputime accounting regression Ivan Delalande
2018-09-13 23:13 ` Ivan Delalande [this message]
2018-09-14  6:57   ` [PATCH 4.9 0/4] Fix softirq time accounting issues on 4.9 Greg Kroah-Hartman
2018-10-11 14:11     ` Greg Kroah-Hartman

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=20180913231317.GB11928@visor \
    --to=colona@arista.com \
    --cc=echron@arista.com \
    --cc=fweisbec@gmail.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=mingo@kernel.org \
    --cc=rabin.vincent@axis.com \
    --cc=stable@vger.kernel.org \
    /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