linux-kernel - Re: 2.6.25.9: system clocks works normally then speeds up 4x...

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1215634125.6149.8.camel@localhost.localdomain>
Date:	Wed, 09 Jul 2008 13:08:45 -0700
From:	john stultz <johnstul@...ibm.com>
To:	Philippe Troin <phil@...i.org>
Cc:	linux-kernel@...r.kernel.org, macro@...ux-mips.org
Subject: Re: 2.6.25.9: system clocks works normally then speeds up 4x...


On Wed, 2008-07-09 at 13:01 -0700, Philippe Troin wrote:
> "john stultz" <johnstul@...ibm.com> writes:
> 
> > On Wed, Jul 9, 2008 at 12:21 PM, Philippe Troin <phil@...i.org> wrote:
> > >
> > > Symptoms:
> > >
> > >  The system boots fine. Clock seems to run normally.
> > >
> > >  Then after a random amount of time (on the current boot, 3 days),
> > >  clock starts to be running 2-4x faster (on the current boot, 4x).
> > >
> > >  I have tried booting with "nohz=off highres=off" but it does not
> > >  help.
> > 
> > Could you provide the output from the following:
> >    sudo cat /sys/devices/system/clocksource/clocksource0/*
> 
> Sure.
> 
> It is:
> available: jiffies tsc 
> current:   jiffies
> 
> > Did this issue occur with 2.6.24 or earlier kernels?
> 
> No.  It started with 2.6.25.
> 
> Interestingly:
> 
>   I've just modified the current clocksource to tsc and the clock went
>   back to its normal speed.
> 
>   Then I reset the current clocksource to jiffies, and the clock went
>   back to its (wrong) 4x speed.
> 
> So it looks like the kernel is counting jiffies 4x too fast.

When you're seeing the issue, can you do the following:
  cat /proc/interrupts > interrupts

  <wait 10 seconds by your wristwatch> 

  cat /proc/interrupts >> interrupts

And send the results?

Could you also try booting with noapic to see if that changes anything?

Maciej: Does this sound related to the recent APIC setup changes?

thanks
-john

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/