Skip to contentSkip to conversation

CFS-devel, latest code

git Applied Dmitry Adamushko 3 participants 5 messages Oct 2, 2007 – Oct 4, 2007

lore
Share & tools
lore
#0 lore raw
Quoted 13 lines · Ingo Molnar
Quoted 9 lines · Dmitry Adamushko

here is a few patches on top of the recent 'sched-dev':

(1) [ proposal ] make timeslices of SCHED_RR tasks constant and not dependent on task's static_prio;

(2) [ cleanup ] calc_weighted() is obsolete, remove it;

(3) [ refactoring ] make dequeue_entity() / enqueue_entity()
and update_stats_dequeue() / update_stats_enqueue() look similar, structure-wise.

Quoted 6 lines

thanks - i've applied all 3 patches of yours.

Quoted 1 line

(compiles well, not functionally tested yet)

(it boots fine here and SCHED_RR seems to work - but i've not tested getinterval.)

/me is guilty... it was a bit broken :-/ here is the fix.

results:

(SCHED_FIFO)

dimm@earth:~/storage/prog$ sudo chrt -f 10 ./rr_interval 
time_slice: 0 : 0

(SCHED_RR)

dimm@earth:~/storage/prog$ sudo chrt 10 ./rr_interval 
time_slice: 0 : 99984800

(SCHED_NORMAL)

dimm@earth:~/storage/prog$ ./rr_interval 
time_slice: 0 : 19996960

(SCHED_NORMAL + a cpu_hog of similar 'weight' on the same CPU --- so should be a half of the previous result)

dimm@earth:~/storage/prog$ taskset 1 ./rr_interval 
time_slice: 0 : 9998480

---

kernel/sched.c +2 -1
index d835cd2..cce22ff 100644
@@ -4745,11 +4745,12 @@ long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
 	else if (p->policy == SCHED_RR)
 		time_slice = DEF_TIMESLICE;
 	else {
+		struct sched_entity *se = &p->se;
 		unsigned long flags;
 		struct rq *rq;
 
 		rq = task_rq_lock(p, &flags);
-		time_slice = sched_slice(&rq->cfs, &p->se);
+		time_slice = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se));
 		task_rq_unlock(rq, &flags);
 	}
 	read_unlock(&tasklist_lock);

---

#1 lore raw

The following patch (sched: disable sleeper_fairness on SCHED_BATCH) seems to break GROUP_SCHED. Although, it may be 'oops'-less due to the possibility of 'p' being always a valid address.

---

kernel/sched_fair.c +2 -3
index 8727d17..a379456 100644
@@ -473,9 +473,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 		vruntime += sched_vslice_add(cfs_rq, se);
 
 	if (!initial) {
-		struct task_struct *p = container_of(se, struct task_struct, se);
-
-		if (sched_feat(NEW_FAIR_SLEEPERS) && p->policy != SCHED_BATCH)
+		if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se) &&
+				task_of(se)->policy != SCHED_BATCH)
 			vruntime -= sysctl_sched_latency;
 
 		vruntime = max_t(s64, vruntime, se->vruntime);

---

#2 lore raw
Quoted 4 lines · Dmitry Adamushko

The following patch (sched: disable sleeper_fairness on SCHED_BATCH) seems to break GROUP_SCHED. Although, it may be 'oops'-less due to the possibility of 'p' being always a valid address.

Thanks for catching it! Patch below looks good to me.

Quoted 22 lines

---

kernel/sched_fair.c +2 -4
index 8727d17..a379456 100644
@@ -473,9 +473,8 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 		vruntime += sched_vslice_add(cfs_rq, se);
 
 	if (!initial) {
-		struct task_struct *p = container_of(se, struct task_struct, se);
-
-		if (sched_feat(NEW_FAIR_SLEEPERS) && p->policy != SCHED_BATCH)
+		if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se) &&
+				task_of(se)->policy != SCHED_BATCH)
 			vruntime -= sysctl_sched_latency;
 
 		vruntime = max_t(s64, vruntime, se->vruntime);
 
---
Signature · 2 lines
Regards,
vatsa
Applied
#3 lore raw
In reply to Dmitry Adamushko
Quoted 3 lines · Dmitry Adamushko

The following patch (sched: disable sleeper_fairness on SCHED_BATCH) seems to break GROUP_SCHED. Although, it may be 'oops'-less due to the possibility of 'p' being always a valid address.

thanks, applied.

Ingo

Applied
#4 lore raw
In reply to Dmitry Adamushko
Quoted 14 lines · Dmitry Adamushko

results:

(SCHED_FIFO)

dimm@earth:~/storage/prog$ sudo chrt -f 10 ./rr_interval 
time_slice: 0 : 0

(SCHED_RR)

dimm@earth:~/storage/prog$ sudo chrt 10 ./rr_interval 
time_slice: 0 : 99984800

(SCHED_NORMAL)

Quoted 7 lines
dimm@earth:~/storage/prog$ ./rr_interval 
time_slice: 0 : 19996960

(SCHED_NORMAL + a cpu_hog of similar 'weight' on the same CPU --- so should be a half of the previous result)

dimm@earth:~/storage/prog$ taskset 1 ./rr_interval 
time_slice: 0 : 9998480

thanks, applied.

Ingo