lkml.org 
[lkml]   [2009]   [Feb]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Negative values in /proc/latency_stats
On Tue, 3 Feb 2009 21:46:09 -0800

> > + * (note: the average latency is the acummulated latency deviced
> > by the number
> > + * of times)
>
> I was surprised at this. Is the stack backtracer sufficiently
> reliable/repeatable for this to work?

yep it is, at least on x86 and x86-64.

>
> > + * Negative latencies (caused by time going backwards) are also
> > explicitly
> > + * skipped.
>
> Are we sure that this was the cause of the problem?

not 100%, but if you add only positive numbers..... the only other
option is an overflow.. but that would be such a huge latency that that
is not very believable.

>
> Which time source is the caller using here, and why is it going
> backwards?

scheduler clock.


--
Arjan van de Ven Intel Open Source Technology Centre
For development, discussion and tips for power savings,
visit http://www.lesswatts.org


\
 
 \ /
  Last update: 2009-02-04 06:59    [W:0.218 / U:0.008 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site