[patch 09/39] sched: SCHED_OTHER vs SCHED_IDLE isolation

From: Greg KH
Date: Wed Feb 18 2009 - 16:38:54 EST


2.6.28-stable review patch. If anyone has any objections, please let us know.

------------------

From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>

commit 6bc912b71b6f33b041cfde93ca3f019cbaa852bc upstream.

Stronger SCHED_IDLE isolation:

- no SCHED_IDLE buddies
- never let SCHED_IDLE preempt on wakeup
- always preempt SCHED_IDLE on wakeup
- limit SLEEPER fairness for SCHED_IDLE.

Signed-off-by: Mike Galbraith <efault@xxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>

---
kernel/sched_fair.c | 30 ++++++++++++++++++++++--------
1 file changed, 22 insertions(+), 8 deletions(-)

--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -681,9 +681,13 @@ place_entity(struct cfs_rq *cfs_rq, stru
unsigned long thresh = sysctl_sched_latency;

/*
- * convert the sleeper threshold into virtual time
+ * Convert the sleeper threshold into virtual time.
+ * SCHED_IDLE is a special sub-class. We care about
+ * fairness only relative to other SCHED_IDLE tasks,
+ * all of which have the same weight.
*/
- if (sched_feat(NORMALIZED_SLEEPER))
+ if (sched_feat(NORMALIZED_SLEEPER) &&
+ task_of(se)->policy != SCHED_IDLE)
thresh = calc_delta_fair(thresh, se);

vruntime -= thresh;
@@ -1328,14 +1332,18 @@ wakeup_preempt_entity(struct sched_entit

static void set_last_buddy(struct sched_entity *se)
{
- for_each_sched_entity(se)
- cfs_rq_of(se)->last = se;
+ if (likely(task_of(se)->policy != SCHED_IDLE)) {
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->last = se;
+ }
}

static void set_next_buddy(struct sched_entity *se)
{
- for_each_sched_entity(se)
- cfs_rq_of(se)->next = se;
+ if (likely(task_of(se)->policy != SCHED_IDLE)) {
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->next = se;
+ }
}

/*
@@ -1382,12 +1390,18 @@ static void check_preempt_wakeup(struct
return;

/*
- * Batch tasks do not preempt (their preemption is driven by
+ * Batch and idle tasks do not preempt (their preemption is driven by
* the tick):
*/
- if (unlikely(p->policy == SCHED_BATCH))
+ if (unlikely(p->policy != SCHED_NORMAL))
return;

+ /* Idle tasks are by definition preempted by everybody. */
+ if (unlikely(curr->policy == SCHED_IDLE)) {
+ resched_task(curr);
+ return;
+ }
+
if (!sched_feat(WAKEUP_PREEMPT))
return;


--
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/