On Thursday 06 July 2006 22:01, Mike Jakubik wrote:> I'm getting a ton of them now, and i found a way to reproduce them.
> Basically i run a compile session in one terminal, say make buildkernel,
> and run top in another. As soon as i run top, the messages appear, and
> they seem to be synchronized with the refresh rate of top, 2 messages
> per refresh. This is on a 6.1-STABLE as of today.
That is partly because when you run top it queries the resource usage of the
various processes via fill_kinfo_proc(). When you don't run top, no one is
asking for the resource usage numbers, so the kernel doesn't waste time
calculating them.
> ---
> calcru: negative runtime of -261273 usec for pid 12 (swi4: clock)
> calcru: negative runtime of -261273 usec for pid 12 (swi4: clock)
> calcru: negative runtime of -259691 usec for pid 12 (swi4: clock)
> ...
In both cases your errors are for a long-running kernel process that's been
up
since boot. What's the uptime on your box?
--
John Baldwin