Yinghai, Balbir, Arjan,
Could you try the below to see if that fully does away with the /0 in
the group scheduler thing?
---
kernel/sched.c | 53 +++++++++++++++++++++++++++++++++--------------------
1 files changed, 33 insertions(+), 20 deletions(-)
diff --git a/kernel/sched.c b/kernel/sched.c
index 0e76b17..45cebe0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1515,30 +1515,33 @@ static unsigned long cpu_avg_load_per_task(int cpu)
#ifdef CONFIG_FAIR_GROUP_SCHED
+struct update_shares_data {
+ spinlock_t lock;
+ unsigned long sum_weight;
+ unsigned long shares;
+ unsigned long rq_weight[NR_CPUS];
+};
+
+static DEFINE_PER_CPU(struct update_shares_data, update_shares_data);
+
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
/*
* Calculate and set the cpu's group shares.
*/
-static void
-update_group_shares_cpu(struct task_group *tg, int cpu,
- unsigned long sd_shares, unsigned long sd_rq_weight,
- unsigned long sd_eff_weight)
+static void update_group_shares_cpu(struct task_group *tg,
+ struct update_shares_data *usd, int cpu)
{
- unsigned long rq_weight;
- unsigned long shares;
+ unsigned long shares, rq_weight;
int boost = 0;
if (!tg->se[cpu])
return;
- rq_weight = tg->cfs_rq[cpu]->rq_weight;
+ rq_weight = usd->rq_weight[cpu];
if (!rq_weight) {
boost = 1;
rq_weight = NICE_0_LOAD;
- if (sd_rq_weight == sd_eff_weight)
- sd_eff_weight += NICE_0_LOAD;
- sd_rq_weight = sd_eff_weight;
}
/*
@@ -1546,7 +1549,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
* shares_i = -----------------------------
* \Sum_j rq_weight_j
*/
- shares = (sd_shares * rq_weight) / sd_rq_weight;
+ shares = (usd->shares * rq_weight) / usd->sum_weight;
shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
if (abs(shares - tg->se[cpu]->load.weight) >
@@ -1555,6 +1558,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
unsigned long flags;
spin_lock_irqsave(&rq->lock, flags);
+ tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
__set_se_shares(tg->se[cpu], shares);
spin_unlock_irqrestore(&rq->lock, flags);
@@ -1568,36 +1572,44 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long weight, rq_weight = 0, eff_weight = 0;
- unsigned long shares = 0;
+ struct update_shares_data *usd = &get_cpu_var(update_shares_data);
+ unsigned long weight, sum_weight = 0, shares = 0;
struct sched_domain *sd = data;
+ unsigned long flags;
int i;
+ spin_lock_irqsave(&usd->lock, flags);
+
for_each_cpu(i, sched_domain_span(sd)) {
+ weight = tg->cfs_rq[i]->load.weight;
+ usd->rq_weight[i] = weight;
+
/*
* If there are currently no tasks on the cpu pretend there
* is one of average load so that when a new task gets to
* run here it will not get delayed by group starvation.
*/
- weight = tg->cfs_rq[i]->load.weight;
- tg->cfs_rq[i]->rq_weight = weight;
- rq_weight += weight;
-
if (!weight)
weight = NICE_0_LOAD;
- eff_weight += weight;
+ sum_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
- if ((!shares && rq_weight) || shares > tg->shares)
+ if ((!shares && sum_weight) || shares > tg->shares)
shares = tg->shares;
if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
shares = tg->shares;
+ usd->sum_weight = sum_weight;
+ usd->shares = shares;
+
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight, eff_weight);
+ update_group_shares_cpu(tg, usd, i);
+
+ spin_unlock_irqrestore(&usd->lock, flags);
+ put_cpu_var(update_shares_data);
return 0;
}
@@ -9449,6 +9461,7 @@ void __init sched_init(void)
init_cfs_rq(&rq->cfs, rq);
init_rt_rq(&rq->rt, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
+ spin_lock_init(&per_cpu(update_shares_data, i).lock);
init_task_group.shares = init_task_group_load;
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
#ifdef CONFIG_CGROUP_SCHED
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|