>I am (or rather, will be once 2.2 stabilizes) working
>on the exact opposite: SCHED_IDLE processes which only
>run when the system's got nothing else to do.
I already have something like that. It's a modification of how niceness
values are interpreted. It uses a range of 11 niceness values to get
the processor, e.g. when there's a process running at nice=0 then no
proces with nice=11 or higher will get the cpu. On the other hand, if
there's a process running at nice=-11 (eg. timidity or mikmod) then no
'normal' process will get the cpu. Processes started just with nice
will still get a little bit of the cpu as usual (that's why the
range is 11 and not 10).
I used it on 2.0.36. This is a version for 2.2.
Peter
--- sched.c.original Mon Feb 8 19:44:50 1999
+++ sched.c Mon Feb 8 23:33:55 1999
@@ -171,7 +171,8 @@
static inline void reschedule_idle(struct task_struct * p)
{
- if (p->policy != SCHED_OTHER || p->counter > current->counter + 3) {
+ if (p->policy != SCHED_OTHER ||
+ p->counter+(p->priority<<2)>=current->counter+(current->priority<<2)) {
current->need_resched = 1;
return;
}
@@ -360,9 +361,9 @@
* Don't do any other calculations if the time slice is
* over..
*/
- weight = p->counter;
- if (weight) {
-
+ weight = p->counter+(p->priority<<2);
+ if (p->counter) {
+
#ifdef __SMP__
/* Give a largish advantage to the same processor... */
/* (this is equivalent to penalizing other processors) */
@@ -373,7 +374,7 @@
/* .. and a slight advantage to the current thread */
if (p->mm == prev->mm)
weight += 1;
- weight += p->priority;
+ weight += 1; /* nice compatibility */
}
return weight;
@@ -716,11 +717,12 @@
}
/* Do we need to re-calculate counters? */
- if (!c) {
+ if (c <= (next->priority << 2)) {
struct task_struct *p;
read_lock(&tasklist_lock);
for_each_task(p)
- p->counter = (p->counter >> 1) + p->priority;
+ p->counter = (p->counter + 41) >> 1;
+
read_unlock(&tasklist_lock);
}
}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/