Modify the way we account for CPU time spent (step 1)

Keep track of time spent by the cpu in various contexts in units of
"cputicks" and scale to real-world microsec^H^H^H^H^H^H^H^Hclock_t
only when somebody wants to inspect the numbers.

For now "cputicks" are still derived from the current timecounter
and therefore things should by definition remain sensible also on
SMP machines.  (The main reason for this first milestone commit is
to verify that hypothesis.)

On slower machines, the avoided multiplications to normalize timestams
at every context switch, comes out as a 5-7% better score on the
unixbench/context1 microbenchmark.  On more modern hardware no change
in performance is seen.

1 files changed, 1 insertions, 1 deletions

diff --git a/sys/sys/pcpu.h b/sys/sys/pcpu.h
index c5c5944..00a3cac 100644
--- a/sys/sys/pcpu.h
+++ b/sys/sys/pcpu.h
@@ -60,7 +60,7 @@ struct pcpu {
 	struct thread	*pc_fpcurthread;	/* Fp state owner */
 	struct thread	*pc_deadthread;		/* Zombie thread or NULL */
 	struct pcb	*pc_curpcb;		/* Current pcb */
-	struct bintime	pc_switchtime;	
+	uint64_t	pc_switchtime;	
 	int		pc_switchticks;
 	u_int		pc_cpuid;		/* This cpu number */
 	cpumask_t	pc_cpumask;		/* This cpu mask */