[34-longterm 095/260] sched: Fix select_idle_sibling() logic in select_task_rq_fair()

From: Paul Gortmaker
Date: Sun Jan 02 2011 - 02:57:25 EST


From: Suresh Siddha <suresh.b.siddha@xxxxxxxxx>

commit 99bd5e2f245d8cd17d040c82d40becdb3efd9b69 upstream.

Issues in the current select_idle_sibling() logic in select_task_rq_fair()
in the context of a task wake-up:

a) Once we select the idle sibling, we use that domain (spanning the cpu that
the task is currently woken-up and the idle sibling that we found) in our
wake_affine() decisions. This domain is completely different from the
domain(we are supposed to use) that spans the cpu that the task currently
woken-up and the cpu where the task previously ran.

b) We do select_idle_sibling() check only for the cpu that the task is
currently woken-up on. If select_task_rq_fair() selects the previously run
cpu for waking the task, doing a select_idle_sibling() check
for that cpu also helps and we don't do this currently.

c) In the scenarios where the cpu that the task is woken-up is busy but
with its HT siblings are idle, we are selecting the task be woken-up
on the idle HT sibling instead of a core that it previously ran
and currently completely idle. i.e., we are not taking decisions based on
wake_affine() but directly selecting an idle sibling that can cause
an imbalance at the SMT/MC level which will be later corrected by the
periodic load balancer.

Fix this by first going through the load imbalance calculations using
wake_affine() and once we make a decision of woken-up cpu vs previously-ran cpu,
then choose a possible idle sibling for waking up the task on.

Signed-off-by: Suresh Siddha <suresh.b.siddha@xxxxxxxxx>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
LKML-Reference: <1270079265.7835.8.camel@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
---
kernel/sched_fair.c | 82 +++++++++++++++++++++++++--------------------------
1 files changed, 40 insertions(+), 42 deletions(-)

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index a29df86..72eb9a6 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1408,29 +1408,48 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
/*
* Try and locate an idle CPU in the sched_domain.
*/
-static int
-select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+static int select_idle_sibling(struct task_struct *p, int target)
{
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
+ struct sched_domain *sd;
int i;

/*
- * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
- * test in select_task_rq_fair) and the prev_cpu is idle then that's
- * always a better target than the current cpu.
+ * If the task is going to be woken-up on this cpu and if it is
+ * already idle, then it is the right target.
+ */
+ if (target == cpu && idle_cpu(cpu))
+ return cpu;
+
+ /*
+ * If the task is going to be woken-up on the cpu where it previously
+ * ran and if it is currently idle, then it the right target.
*/
- if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+ if (target == prev_cpu && idle_cpu(prev_cpu))
return prev_cpu;

/*
- * Otherwise, iterate the domain and find an elegible idle cpu.
+ * Otherwise, iterate the domains and find an elegible idle cpu.
*/
- for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
- if (!cpu_rq(i)->cfs.nr_running) {
- target = i;
+ for_each_domain(target, sd) {
+ if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
break;
+
+ for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+ if (idle_cpu(i)) {
+ target = i;
+ break;
+ }
}
+
+ /*
+ * Lets stop looking for an idle sibling when we reached
+ * the domain that spans the current cpu and prev_cpu.
+ */
+ if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
+ cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+ break;
}

return target;
@@ -1454,7 +1473,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
int new_cpu = cpu;
- int want_affine = 0, cpu_idle = !current->pid;
+ int want_affine = 0;
int want_sd = 1;
int sync = wake_flags & WF_SYNC;

@@ -1494,36 +1513,13 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
}

/*
- * While iterating the domains looking for a spanning
- * WAKE_AFFINE domain, adjust the affine target to any idle cpu
- * in cache sharing domains along the way.
+ * If both cpu and prev_cpu are part of this domain,
+ * cpu is a valid SD_WAKE_AFFINE target.
*/
- if (want_affine) {
- int target = -1;
-
- /*
- * If both cpu and prev_cpu are part of this domain,
- * cpu is a valid SD_WAKE_AFFINE target.
- */
- if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
- target = cpu;
-
- /*
- * If there's an idle sibling in this domain, make that
- * the wake_affine target instead of the current cpu.
- */
- if (!cpu_idle && tmp->flags & SD_SHARE_PKG_RESOURCES)
- target = select_idle_sibling(p, tmp, target);
-
- if (target >= 0) {
- if (tmp->flags & SD_WAKE_AFFINE) {
- affine_sd = tmp;
- want_affine = 0;
- if (target != cpu)
- cpu_idle = 1;
- }
- cpu = target;
- }
+ if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
+ cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+ affine_sd = tmp;
+ want_affine = 0;
}

if (!want_sd && !want_affine)
@@ -1554,8 +1550,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_
#endif

if (affine_sd) {
- if (cpu_idle || cpu == prev_cpu || wake_affine(affine_sd, p, sync))
- return cpu;
+ if (cpu == prev_cpu || wake_affine(affine_sd, p, sync))
+ return select_idle_sibling(p, cpu);
+ else
+ return select_idle_sibling(p, prev_cpu);
}

while (sd) {
--
1.7.3.3

--
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/