Messages in this thread | | | Date | Tue, 3 Feb 2009 21:55:52 -0800 | From | Arjan van de Ven <> | Subject | Re: 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
| |