Re: strange `time' results on dual-processor P6 systems

Alan Cox (
Fri, 31 Jan 1997 20:13:23 +0000 (GMT)

> The CPU's are spinning in kernel mode on the master kernel lock we
> have for SMP. Userland is of course multi threaded on SMP, but the
> kernel is simgle threaded so all those faults being done by your test
> program must be processed serially.

Actually dave the kernel/user accounting for CPU > 0 is backwards ;)