Re: [PATCH V2 2/2] sched: Remove un-necessary iteration over scheddomains to update nr_busy_cpus

From: Preeti U Murthy
Date: Tue Oct 29 2013 - 23:23:39 EST


The changelog has missed mentioning the introduction of sd_asym per_cpu sched domain.
Apologies for this. The patch with the changelog including mention of sd_asym is
pasted below.

Regards
Preeti U Murthy

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

sched: Remove un-necessary iteration over sched domains to update nr_busy_cpus

From: Preeti U Murthy <preeti@xxxxxxxxxxxxxxxxxx>

nr_busy_cpus parameter is used by nohz_kick_needed() to find out the number
of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES flag set.
Therefore instead of updating nr_busy_cpus at every level of sched domain,
since it is irrelevant, we can update this parameter only at the parent
domain of the sd which has this flag set. Introduce a per-cpu parameter
sd_busy which represents this parent domain.

In nohz_kick_needed() we directly query the nr_busy_cpus parameter
associated with the groups of sd_busy.

By associating sd_busy with the highest domain which has
SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains which could
have this flag set and trigger nohz_idle_balancing if any of the levels have
more than one busy cpu.

sd_busy is irrelevant for asymmetric load balancing. However sd_asym has been
introduced to represent the highest sched domain which has SD_ASYM_PACKING flag set
so that it can be queried directly when required.

While we are at it, we might as well change the nohz_idle parameter to be
updated at the sd_busy domain level alone and not the base domain level of a CPU.
This will unify the concept of busy cpus at just one level of sched domain
where it is currently used.

Signed-off-by: Preeti U Murthy<preeti@xxxxxxxxxxxxxxxxxx>
---
kernel/sched/core.c | 6 ++++++
kernel/sched/fair.c | 38 ++++++++++++++++++++------------------
kernel/sched/sched.h | 2 ++
3 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c06b8d3..e6a6244 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5271,6 +5271,8 @@ DEFINE_PER_CPU(struct sched_domain *, sd_llc);
DEFINE_PER_CPU(int, sd_llc_size);
DEFINE_PER_CPU(int, sd_llc_id);
DEFINE_PER_CPU(struct sched_domain *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain *, sd_busy);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym);

static void update_top_cache_domain(int cpu)
{
@@ -5282,6 +5284,7 @@ static void update_top_cache_domain(int cpu)
if (sd) {
id = cpumask_first(sched_domain_span(sd));
size = cpumask_weight(sched_domain_span(sd));
+ rcu_assign_pointer(per_cpu(sd_busy, cpu), sd->parent);
}

rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
@@ -5290,6 +5293,9 @@ static void update_top_cache_domain(int cpu)

sd = lowest_flag_domain(cpu, SD_NUMA);
rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
+
+ sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
+ rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
}

/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e9c9549..8602b2c 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6515,16 +6515,16 @@ static inline void nohz_balance_exit_idle(int cpu)
static inline void set_cpu_sd_state_busy(void)
{
struct sched_domain *sd;
+ int cpu = smp_processor_id();

rcu_read_lock();
- sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+ sd = rcu_dereference(per_cpu(sd_busy, cpu));

if (!sd || !sd->nohz_idle)
goto unlock;
sd->nohz_idle = 0;

- for (; sd; sd = sd->parent)
- atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+ atomic_inc(&sd->groups->sgp->nr_busy_cpus);
unlock:
rcu_read_unlock();
}
@@ -6532,16 +6532,16 @@ unlock:
void set_cpu_sd_state_idle(void)
{
struct sched_domain *sd;
+ int cpu = smp_processor_id();

rcu_read_lock();
- sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+ sd = rcu_dereference(per_cpu(sd_busy, cpu));

if (!sd || sd->nohz_idle)
goto unlock;
sd->nohz_idle = 1;

- for (; sd; sd = sd->parent)
- atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+ atomic_dec(&sd->groups->sgp->nr_busy_cpus);
unlock:
rcu_read_unlock();
}
@@ -6748,6 +6748,8 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
{
unsigned long now = jiffies;
struct sched_domain *sd;
+ struct sched_group_power *sgp;
+ int nr_busy;

if (unlikely(idle_cpu(cpu)))
return 0;
@@ -6773,22 +6775,22 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
goto need_kick;

rcu_read_lock();
- for_each_domain(cpu, sd) {
- struct sched_group *sg = sd->groups;
- struct sched_group_power *sgp = sg->sgp;
- int nr_busy = atomic_read(&sgp->nr_busy_cpus);
+ sd = rcu_dereference(per_cpu(sd_busy, cpu));

- if (sd->flags & SD_SHARE_PKG_RESOURCES && nr_busy > 1)
- goto need_kick_unlock;
+ if (sd) {
+ sgp = sd->groups->sgp;
+ nr_busy = atomic_read(&sgp->nr_busy_cpus);

- if (sd->flags & SD_ASYM_PACKING
- && (cpumask_first_and(nohz.idle_cpus_mask,
- sched_domain_span(sd)) < cpu))
+ if (nr_busy > 1)
goto need_kick_unlock;
-
- if (!(sd->flags & (SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING)))
- break;
}
+
+ sd = rcu_dereference(per_cpu(sd_asym, cpu));
+
+ if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
+ sched_domain_span(sd)) < cpu))
+ goto need_kick_unlock;
+
rcu_read_unlock();
return 0;

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ffc7087..c8cb145 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -623,6 +623,8 @@ DECLARE_PER_CPU(struct sched_domain *, sd_llc);
DECLARE_PER_CPU(int, sd_llc_size);
DECLARE_PER_CPU(int, sd_llc_id);
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain *, sd_busy);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym);

struct sched_group_power {
atomic_t ref;

--
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/