Strange timing problems with BETA7

[Marius Strobl]

On Fri, Oct 15, 2004 at 10:54:39AM +0200, Herve Boulouis wrote:
> Le 14/10/2004 à 09:19, Ken Smith a écrit:
> > 
> > ISO's?  This looks like the configuration before the final set
> > of timer related patches, I think the last chunk went in late
> > last week.  If you cvsup now you should get everything.  Your
> 
> After 14 hours of uptime, I'm seeing the same symptoms than before
> (ping & netstat stuck, ...) but there is less errors in dmesg :
> 
> pid 1095 (wget), uid 0: exited on signal 6 (core dumped)
> calcru: negative runtime of -967798 usec for pid 1119 (traceroute)
> calcru: negative runtime of -911825 usec for pid 1126 (vi)
> calcru: runtime went backwards from 13956864383 usec to 13956492689 usec for pid 12 (idle: cpu0)
> calcru: runtime went backwards from 12797934342 usec to 12797704335 usec for pid 11 (idle: cpu1)
> calcru: runtime went backwards from 13956864383 usec to 13956492689 usec for pid 12 (idle: cpu0)
> calcru: runtime went backwards from 13956864383 usec to 13956138414 usec for pid 12 (idle: cpu0)
> calcru: runtime went backwards from 12797934342 usec to 12797574096 usec for pid 11 (idle: cpu1)
> calcru: runtime went backwards from 13956864383 usec to 13956138414 usec for pid 12 (idle: cpu0)
> calcru: runtime went backwards from 13956864383 usec to 13955427447 usec for pid 12 (idle: cpu0)
> calcru: runtime went backwards from 12797934342 usec to 12797008556 usec for pid 11 (idle: cpu1)
> calcru: runtime went backwards from 13956864383 usec to 13955427447 usec for pid 12 (idle: cpu0)
> calcru: runtime went backwards from 12797934342 usec to 12797008556 usec for pid 11 (idle: cpu1)
> calcru: negative runtime of -282593 usec for pid 1140 (more)
> 
> The strange thing is that the negative latencies in traceroute are
> definitely gone, could there be 2 different problems here ?
> 

Are there other problems like time elapsing too fast on that machine?