Add scheduler CORE, the work I have done half a year ago, recent,

I picked it up again. The scheduler is forked from ULE, but the
algorithm to detect an interactive process is almost completely
different with ULE, it comes from Linux paper "Understanding the
Linux 2.6.8.1 CPU Scheduler", although I still use same word
"score" as a priority boost in ULE scheduler.

Briefly, the scheduler has following characteristic:
1. Timesharing process's nice value is seriously respected,
   timeslice and interaction detecting algorithm are based
   on nice value.
2. per-cpu scheduling queue and load balancing.
3. O(1) scheduling.
4. Some cpu affinity code in wakeup path.
5. Support POSIX SCHED_FIFO and SCHED_RR.
Unlike scheduler 4BSD and ULE which using fuzzy RQ_PPQ, the scheduler
uses 256 priority queues. Unlike ULE which using pull and push, the
scheduelr uses pull method, the main reason is to let relative idle
cpu do the work, but current the whole scheduler is protected by the
big sched_lock, so the benefit is not visible, it really can be worse
than nothing because all other cpu are locked out when we are doing
balancing work, which the 4BSD scheduelr does not have this problem.
The scheduler does not support hyperthreading very well, in fact,
the scheduler does not make the difference between physical CPU and
logical CPU, this should be improved in feature. The scheduler has
priority inversion problem on MP machine, it is not good for
realtime scheduling, it can cause realtime process starving.
As a result, it seems the MySQL super-smack runs better on my
Pentium-D machine when using libthr, despite on UP or SMP kernel.

sys/amd64/conf/GENERIC

@@ -28,6 +28,7 @@ makeoptions	DEBUG=-g		# Build kernel with gdb(1) debug symbols
 
 #options 	SCHED_ULE		# ULE scheduler
 options 	SCHED_4BSD		# 4BSD scheduler
+#options 	SCHED_CORE		# CORE scheduler
 options 	PREEMPTION		# Enable kernel thread preemption
 options 	INET			# InterNETworking
 options 	INET6			# IPv6 communications protocols

sys/conf/NOTES

@@ -166,6 +166,7 @@ options 	ROOTDEVNAME=\"ufs:da0s2e\"
 # over time.
 #
 options 	SCHED_4BSD
+#options 	SCHED_CORE
 #options 	SCHED_ULE
 
 #####################################################################

sys/conf/files

@@ -1324,6 +1324,7 @@ kern/linker_if.m		standard
 kern/md4c.c			optional netsmb
 kern/md5c.c			standard
 kern/sched_4bsd.c		optional sched_4bsd
+kern/sched_core.c		optional sched_core
 kern/sched_ule.c		optional sched_ule
 kern/serdev_if.m		optional puc | scc
 kern/subr_autoconf.c		standard

sys/conf/options

@@ -128,6 +128,7 @@ PPS_SYNC	opt_ntp.h
 PREEMPTION	opt_sched.h
 QUOTA
 SCHED_4BSD	opt_sched.h
+SCHED_CORE	opt_sched.h
 SCHED_ULE	opt_sched.h
 SHOW_BUSYBUFS
 SLEEPQUEUE_PROFILING

sys/i386/conf/GENERIC

@@ -30,6 +30,7 @@ makeoptions	DEBUG=-g		# Build kernel with gdb(1) debug symbols
 
 #options 	SCHED_ULE		# ULE scheduler
 options 	SCHED_4BSD		# 4BSD scheduler
+#options 	SCHED_CORE		# CORE scheduler
 options 	PREEMPTION		# Enable kernel thread preemption
 options 	INET			# InterNETworking
 options 	INET6			# IPv6 communications protocols

sys/kern/kern_clock.c

@@ -201,6 +201,7 @@ hardclock_cpu(int usermode)
 	 * Run current process's virtual and profile time, as needed.
 	 */
 	mtx_lock_spin_flags(&sched_lock, MTX_QUIET);
+	sched_tick();
 	if (p->p_flag & P_SA) {
 		/* XXXKSE What to do? */
 	} else {

sys/kern/kern_switch.c

@@ -308,7 +308,12 @@ adjustrunqueue( struct thread *td, int newpri)
 	if ((td->td_proc->p_flag & P_HADTHREADS) == 0) {
 		/* We only care about the kse in the run queue. */
 		td->td_priority = newpri;
-		if (ke->ke_rqindex != (newpri / RQ_PPQ)) {
+#ifndef SCHED_CORE
+		if (ke->ke_rqindex != (newpri / RQ_PPQ))
+#else
+		if (ke->ke_rqindex != newpri)
+#endif
+		{
 			sched_rem(td);
 			sched_add(td, SRQ_BORING);
 		}

sys/kern/sched_4bsd.c

@@ -1386,5 +1386,10 @@ sched_pctcpu(struct thread *td)
 
 	return (0);
 }
+
+void
+sched_tick(void)
+{
+}
 #define KERN_SWITCH_INCLUDE 1
 #include "kern/kern_switch.c"

sys/kern/sched_ule.c

@@ -2007,5 +2007,10 @@ sched_sizeof_thread(void)
 {
 	return (sizeof(struct thread) + sizeof(struct td_sched));
 }
+
+void
+sched_tick(void)
+{
+}
 #define KERN_SWITCH_INCLUDE 1
 #include "kern/kern_switch.c"

sys/sys/sched.h

@@ -78,6 +78,7 @@ void	sched_wakeup(struct thread *td);
 void	sched_add(struct thread *td, int flags);
 void	sched_clock(struct thread *td);
 void	sched_rem(struct thread *td);
+void	sched_tick(void);
 
 /*
  * Binding makes cpu affinity permanent while pinning is used to temporarily