Re: [PATCH] kernel <linux-2.6.11.10> kernel/sched.c

[chen Shang <shangcs@gmail.com>]

I minimized my patch and against to 2.6.12-rc4 this time, see below.

The new schedstat fields are for the test propose only, so I removed
them completedly from patch. Theoritically, requeue_task() is always
cheaper than dequeue_task() followed by enqueue_task(). So, if 99% of
priority recalculation trigger requeue_task(), it will save.

In addition, my load is to build the kernel, which took around 30
minutes with around 30% CPU usage on 2x2 processors (duel processors
with HT enable).
Here is the statistics:
         
CPU0: priority_changed (669 times), priority_unchanged(335,138 times)
CPU1: priority_changed (784 times), priority_unchanged(342,419 times)
CPU2: priority_changed (782 times), priority_unchanged(283,494 times)
CPU3: priority_changed (872 times), priority_unchanged(365,865 times)

Thanks,
-chen


/*=====Patch=====*/
--- linux-2.6.12-rc4.orig/kernel/sched.c	2005-05-19 14:57:55.000000000 -0700
+++ linux-2.6.12-rc4/kernel/sched.c	2005-05-19 23:47:22.000000000 -0700
@@ -2613,7 +2613,7 @@
 	struct list_head *queue;
 	unsigned long long now;
 	unsigned long run_time;
-	int cpu, idx;
+	int cpu, idx, prio;
 
 	/*
 	 * Test if we are atomic.  Since do_exit() needs to call into
@@ -2735,9 +2735,17 @@
 			delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;
 
 		array = next->array;
-		dequeue_task(next, array);
+		prio = next->prio;
+		
 		recalc_task_prio(next, next->timestamp + delta);
-		enqueue_task(next, array);
+
+		if (unlikely(prio != next->prio))
+		{
+			dequeue_task(next, array);
+			enqueue_task(next, array);
+		}
+		else
+			requeue_task(next, array);
 	}
 	next->activated = 0;
 switch_tasks: