Skip to contentSkip to conversation

sched rsdl fix for 0.28

PATCH Con Kolivas 2 participants 4 messages Mar 10, 2007 – Mar 11, 2007

lore
Share & tools
lore
#0 lore raw

Here's a big bugfix for sched rsdl 0.28

---
 kernel/sched.c |    7 +++++++
 1 file changed, 7 insertions(+)
kernel/sched.c +7 -0
Index: linux-2.6.21-rc3-mm2/kernel/sched.c
===================================================================
@@ -3328,6 +3328,13 @@ static inline void rotate_runqueue_prior
 	int new_prio_level, remaining_quota = rq_quota(rq, rq->prio_level);
 	struct prio_array *array = rq->active;
 
+	/*
+	 * Make sure we don't have tasks still on the active array that
+	 * haven't run due to not preempting (merging or smp balancing)
+	 */
+	if (find_next_bit(rq->dyn_bitmap, MAX_PRIO, MAX_RT_PRIO) <
+		rq->prio_level)
+			return;
 	if (rq->prio_level > MAX_PRIO - 2) {
 		/* Major rotation required */
 		struct prio_array *new_queue = rq->expired;
Signature · 1 line
-ck
#1 lore raw
Quoted 1 line · Con Kolivas

sched rsdl fix

Doesn't change a thing. Always breaks at the same place (though depending on hardware timings? the trace is not always the same). Pretty sure nothing happens before this failure

Signature · 1 line
Nicolas Mailhot
#2 lore raw
Quoted 6 lines · Nicolas Mailhot
Quoted 1 line · Con Kolivas

sched rsdl fix

Doesn't change a thing. Always breaks at the same place (though depending on hardware timings? the trace is not always the same). Pretty sure nothing happens before this failure

Bummer. The only other thing to try is v0.29 posted recently. I still haven't got a good way to reproduce this locally but I'll keep trying. Thanks for testing.

Signature · 1 line
-ck
#3 lore raw
Quoted 11 lines · Con Kolivas
Quoted 6 lines · Nicolas Mailhot
Quoted 1 line · Con Kolivas

sched rsdl fix

Doesn't change a thing. Always breaks at the same place (though depending on hardware timings? the trace is not always the same). Pretty sure nothing happens before this failure

Bummer. The only other thing to try is v0.29 posted recently. I still haven't got a good way to reproduce this locally but I'll keep trying. Thanks for testing.

Oh and if that oopses and you still have the time, could you please test 0.29 on 2.6.20.2 (available from same directory).

Signature · 1 line
-ck