[PATCH] [sched] redundant reschedule when set_user_nice() boosts a prio of a task from the "expired" array

[Dmitry Adamushko]

Ingo,

following the conversation on "a redundant reschedule call in set_user_prio()",
here is a possible approach.

The patch is somewhat intrusive as it even dares to adapt TASK_PREEMPTS_CURR().

Nevertheless, this adaptation seems to be ok with all the current use-cases.

Presupposition: TASK_PREEMPTS_CURR(p, rq) will /never/ be used as "a
mere prio comparator" - e.g. to make decisions on which array a task
has to be placed in.


=====

o  Make TASK_PREEMPTS_CURR(task, rq) return "true" only if the task's
prio is higher than the current's one and the task is in the "active"
array.
This ensures we don't make redundant resched_task() calls when the
task is in the "expired" array (as may happen now in set_user_prio(),
rt_mutex_setprio() and pull_task() ) ;

o  generilise conditions for a call to resched_task() in
set_user_nice(), rt_mutex_setprio() and sched_setscheduler()

Signed-off-by: Dmitry Adamushko <dmitry.adamushko@xxxxxxxxx>
--

--- linux-2.6.21-rc5/kernel/sched-orig.c        2007-04-04
18:26:19.000000000 +0200
+++ linux-2.6.21-rc5/kernel/sched.c     2007-04-04 18:26:43.000000000 +0200
@@ -168,7 +168,7 @@ unsigned long long __attribute__((weak))
               (MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))

#define TASK_PREEMPTS_CURR(p, rq) \
-       ((p)->prio < (rq)->curr->prio)
+       (((p)->prio < (rq)->curr->prio) && ((p)->array == (rq)->active))

#define SCALE_PRIO(x, prio) \
       max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_TIMESLICE)
@@ -3847,13 +3847,13 @@ void rt_mutex_setprio(struct task_struct
       struct prio_array *array;
       unsigned long flags;
       struct rq *rq;
-       int oldprio;
+       int delta;

       BUG_ON(prio < 0 || prio > MAX_PRIO);

       rq = task_rq_lock(p, &flags);

-       oldprio = p->prio;
+       delta = prio - p->prio;
       array = p->array;
       if (array)
               dequeue_task(p, array);
@@ -3869,13 +3869,10 @@ void rt_mutex_setprio(struct task_struct
               enqueue_task(p, array);
               /*
                * Reschedule if we are currently running on this runqueue and
-                * our priority decreased, or if we are not currently running on
-                * this runqueue and our priority is higher than the current's
+                * our priority decreased, or if our priority became higher
+                * than the current's.
                */
-               if (task_running(rq, p)) {
-                       if (p->prio > oldprio)
-                               resched_task(rq->curr);
-               } else if (TASK_PREEMPTS_CURR(p, rq))
+               if (TASK_PREEMPTS_CURR(p, rq) || (delta > 0 &&
task_running(rq, p)))
                       resched_task(rq->curr);
       }
       task_rq_unlock(rq, &flags);
@@ -3923,10 +3920,11 @@ void set_user_nice(struct task_struct *p
               enqueue_task(p, array);
               inc_raw_weighted_load(rq, p);
               /*
-                * If the task increased its priority or is running and
-                * lowered its priority, then reschedule its CPU:
+                * Reschedule if we are currently running on this runqueue and
+                * our priority decreased, or if our priority became higher
+                * than the current's.
                */
-               if (delta < 0 || (delta > 0 && task_running(rq, p)))
+               if (TASK_PREEMPTS_CURR(p, rq) || (delta > 0 &&
task_running(rq, p)))
                       resched_task(rq->curr);
       }
out_unlock:
@@ -4153,13 +4151,10 @@ recheck:
               __activate_task(p, rq);
               /*
                * Reschedule if we are currently running on this runqueue and
-                * our priority decreased, or if we are not currently running on
-                * this runqueue and our priority is higher than the current's
+                * our priority decreased, or our priority became higher
+                * than the current's.
                */
-               if (task_running(rq, p)) {
-                       if (p->prio > oldprio)
-                               resched_task(rq->curr);
-               } else if (TASK_PREEMPTS_CURR(p, rq))
+               if (TASK_PREEMPTS_CURR(p, rq) || (task_running(rq, p)
&& p->prio > oldprio))
                       resched_task(rq->curr);
       }
       __task_rq_unlock(rq);

=====

--
Best regards,
Dmitry Adamushko
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/