Re: [PATCH] clocksource, prevent overflow in clocksource_cyc2ns

[Prarit Bhargava <prarit@redhat.com>]

On 04/19/2012 02:12 PM, John Stultz wrote:
> On 04/19/2012 05:52 AM, Thomas Gleixner wrote:
>> On Thu, 19 Apr 2012, Thomas Gleixner wrote:
>>
>>> We should think about the reasons why we have interrupts disabled for
>>> so much time. Is that really, really necessary ?
>> I'm not against making the clocksource code more robust, but I don't
>> want to add crap there just to cope with complete madness elsewhere.
>>
> 
> Very much agreed.

Hi John and Thomas,

After much analysis I have good news to report.  The good news is that the
problem with the random tsc failures was chased down to a script left running in
which sysrq-t's were executed over ping packets.  This, as I've previously
pointed out, can cause the tsc to be erroneously marked unstable.

[Aside: I hit myself with a big cluebat when I realized that all the failures
were occurring at the same wall-clock time, 3:00AM.  That couldn't be a
coincidence.]

I'm working with lwoodman to figure out a way to get rid of the locking (as
suggested by you Thomas) around the sysrq code.

P.

> -john
>