Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 30 Nov 2020 14:10:51 +0100
From:      Mateusz Guzik <mjguzik@gmail.com>
To:        current@freebsd.org, Mateusz Guzik <mjguzik@gmail.com>
Subject:   Re: Laptop exhibits erratic responsiveness
Message-ID:  <CAGudoHEZvoj5s2bOz_atg9oPQM=24i5ydGZVebuLQAu0nbS0TA@mail.gmail.com>
In-Reply-To: <X8Tpg1P%2BXQc7iTNJ@albert.catwhisker.org>
References:  <X8JVn/PIPuLzsWuQ@albert.catwhisker.org> <CADrOrms8fmf9asttPw%2B4B%2BKL7A4svAKx0dDHSuDnEVvxGWiX0Q@mail.gmail.com> <X8OsLaVToS1V1zoX@albert.catwhisker.org> <CAGudoHHevDxuvwLO2QMrMNfvG0vWSU=v9gHLbH0eMFDt8p0FWg@mail.gmail.com> <X8Tpg1P%2BXQc7iTNJ@albert.catwhisker.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On 11/30/20, David Wolfskill <david@catwhisker.org> wrote:
> On Sun, Nov 29, 2020 at 03:20:15PM +0100, Mateusz Guzik wrote:
>> On 11/29/20, David Wolfskill <david@catwhisker.org> wrote:
>> > On Sat, Nov 28, 2020 at 10:47:57AM -0500, Jonathan Looney wrote:
>> >> FWIW, I would try running lockstat on the box. (My supposition is that
>> >> the
>> >> delay is due to a lock. That could be incorrect.  Lockstat may provide
>> >> some
>> >> clue as to whether this is a line of inquiry worth pursuing.)
>> >> ....
>> >
>> > Thanks (again), Jonathan.
>> >
>> > So... I did that (during this morning's daily upgrade cycle); the
>> > results may be "of interest" to some.
>> ...
>> > http://www.catwhisker.org/~david/FreeBSD/head/lockstat/README
>> ...
>>
>> According to the data you got the entire kernel "freezes" every 11-12
>> seconds. So something way off is going on there.
>>
>> Given that the bug seems to be reproducible I think it would be best
>> if you just bisected to the offending commit.
>>
>> --
>> Mateusz Guzik <mjguzik gmail.com>
>
> I had thought that the issue arose  (as noted in my initial message)
> around 09 Nov, which was the day that my daily update on head went from
> r367484 to r367517.
>
> So for my inital attempt at a "before the breakage" kernel (& world), I
> "updated" sources to r367444, as I had updated to that revision on 07
> Nov.
>
> Testing (again, via "ping albert") still showed most RTTs around 0.600
> ms, but (around) every 11th packet, I would see an RTT in the 400 - 650
> ms range -- around a factor of 1000(ish).  So while I was not seeing
> RTTs in excess of 68 seconds (as I did at least one time for the initial
> message), I believe(d) that the underlying issue still existed at
> r367444.
>
> Lather, rinse, repeat -- for:
>
> * r367484 (from 08 Nov)
> * r367243 (from 01 Nov)
> * r366312 (from 01 Oct)
> * r363759 (from 01 Aug)
>
> At this point, I was questioning many assumptions, so I cleared /usr/obj
> completely and then updated back to r368143... and the issue remained.
>
> (The laptop was quite busy yesterday.)
>
> I definitely do NOT see anything like this running stable/12 (presently
> at r368181).
>
> I will try some experiments with another laptop (a newer one, for which
> the built-in mouse is detected weirdly, making it annoying to use for me
> -- but I can still ping from it).
>

As a sanity check, does the issue manifest itself if you build a
GENERIC-NODEBUG kernel?

-- 
Mateusz Guzik <mjguzik gmail.com>



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAGudoHEZvoj5s2bOz_atg9oPQM=24i5ydGZVebuLQAu0nbS0TA>