[RFC PATCH v5 9/9] sched/fair: Provide idle search schedstats
From: Chen Jinghuang
Date: Fri Mar 20 2026 - 02:23:26 EST
From: Steve Sistare <steven.sistare@xxxxxxxxxx>
Add schedstats to measure the effectiveness of searching for idle CPUs
and stealing tasks. This is a temporary patch intended for use during
development only. SCHEDSTAT_VERSION is bumped to 16, and the following
fields are added to the per-CPU statistics of /proc/schedstat:
field 10: # of times select_idle_sibling "easily" found an idle CPU --
prev or target is idle.
field 11: # of times select_idle_sibling searched and found an idle cpu.
field 12: # of times select_idle_sibling searched and found an idle core.
field 13: # of times select_idle_sibling failed to find anything idle.
field 14: time in nanoseconds spent in functions that search for idle
CPUs and search for tasks to steal.
field 15: # of times an idle CPU steals a task from another CPU.
field 16: # of times try_steal finds overloaded CPUs but no task is
migratable.
Signed-off-by: Steve Sistare <steven.sistare@xxxxxxxxxx>
Signed-off-by: Chen Jinghuang <chenjinghuang2@xxxxxxxxxx>
---
kernel/sched/core.c | 31 +++++++++++++++++++++++--
kernel/sched/fair.c | 54 ++++++++++++++++++++++++++++++++++++++++----
kernel/sched/sched.h | 9 ++++++++
kernel/sched/stats.c | 9 ++++++++
kernel/sched/stats.h | 13 +++++++++++
5 files changed, 109 insertions(+), 7 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 759777694c78..841a4ca7e173 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4505,17 +4505,44 @@ static int sysctl_numa_balancing(const struct ctl_table *table, int write,
DEFINE_STATIC_KEY_FALSE(sched_schedstats);
+unsigned long schedstat_skid;
+
+static void compute_skid(void)
+{
+ int i, n = 0;
+ s64 t;
+ int skid = 0;
+
+ for (i = 0; i < 100; i++) {
+ t = local_clock();
+ t = local_clock() - t;
+ if (t > 0 && t < 1000) { /* only use sane samples */
+ skid += (int) t;
+ n++;
+ }
+ }
+
+ if (n > 0)
+ schedstat_skid = skid / n;
+ else
+ schedstat_skid = 0;
+ pr_info("schedstat_skid = %lu\n", schedstat_skid);
+}
+
static void set_schedstats(bool enabled)
{
- if (enabled)
+ if (enabled) {
+ compute_skid();
static_branch_enable(&sched_schedstats);
- else
+ } else {
static_branch_disable(&sched_schedstats);
+ }
}
void force_schedstat_enabled(void)
{
if (!schedstat_enabled()) {
+ compute_skid();
pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
static_branch_enable(&sched_schedstats);
}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 500215a57392..ba2b9f811135 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5091,29 +5091,35 @@ static inline void rq_idle_stamp_clear(struct rq *rq)
static void overload_clear(struct rq *rq)
{
struct sparsemask *overload_cpus;
+ unsigned long time;
if (!sched_feat(STEAL))
return;
+ time = schedstat_start_time();
rcu_read_lock();
overload_cpus = rcu_dereference(rq->cfs_overload_cpus);
if (overload_cpus)
sparsemask_clear_elem(overload_cpus, rq->cpu);
rcu_read_unlock();
+ schedstat_end_time(rq->find_time, time);
}
static void overload_set(struct rq *rq)
{
struct sparsemask *overload_cpus;
+ unsigned long time;
if (!sched_feat(STEAL))
return;
+ time = schedstat_start_time();
rcu_read_lock();
overload_cpus = rcu_dereference(rq->cfs_overload_cpus);
if (overload_cpus)
sparsemask_set_elem(overload_cpus, rq->cpu);
rcu_read_unlock();
+ schedstat_end_time(rq->find_time, time);
}
static int try_steal(struct rq *this_rq, struct rq_flags *rf);
@@ -7830,6 +7836,16 @@ static inline bool asym_fits_cpu(unsigned long util,
return true;
}
+#define SET_STAT(STAT) \
+ do { \
+ if (schedstat_enabled()) { \
+ struct rq *rq = this_rq(); \
+ \
+ if (rq) \
+ __schedstat_inc(rq->STAT); \
+ } \
+ } while (0)
+
/*
* Try and locate an idle core/thread in the LLC cache domain.
*/
@@ -7857,8 +7873,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
lockdep_assert_irqs_disabled();
if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
- asym_fits_cpu(task_util, util_min, util_max, target))
+ asym_fits_cpu(task_util, util_min, util_max, target)) {
+ SET_STAT(found_idle_cpu_easy);
return target;
+ }
/*
* If the previous CPU is cache affine and idle, don't be stupid:
@@ -7868,8 +7886,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
asym_fits_cpu(task_util, util_min, util_max, prev)) {
if (!static_branch_unlikely(&sched_cluster_active) ||
- cpus_share_resources(prev, target))
+ cpus_share_resources(prev, target)) {
+ SET_STAT(found_idle_cpu_easy);
return prev;
+ }
prev_aff = prev;
}
@@ -7887,6 +7907,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
prev == smp_processor_id() &&
this_rq()->nr_running <= 1 &&
asym_fits_cpu(task_util, util_min, util_max, prev)) {
+ SET_STAT(found_idle_cpu_easy);
return prev;
}
@@ -7901,8 +7922,10 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
if (!static_branch_unlikely(&sched_cluster_active) ||
- cpus_share_resources(recent_used_cpu, target))
+ cpus_share_resources(recent_used_cpu, target)) {
+ SET_STAT(found_idle_cpu_easy);
return recent_used_cpu;
+ }
} else {
recent_used_cpu = -1;
@@ -7924,13 +7947,16 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
*/
if (sd) {
i = select_idle_capacity(p, sd, target);
+ SET_STAT(found_idle_cpu_capacity);
return ((unsigned)i < nr_cpumask_bits) ? i : target;
}
}
sd = rcu_dereference_all(per_cpu(sd_llc, target));
- if (!sd)
+ if (!sd) {
+ SET_STAT(nofound_idle_cpu);
return target;
+ }
if (sched_smt_active()) {
has_idle_core = test_idle_cores(target);
@@ -7943,8 +7969,12 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
}
i = select_idle_cpu(p, sd, has_idle_core, target);
- if ((unsigned)i < nr_cpumask_bits)
+ if ((unsigned)i < nr_cpumask_bits) {
+ SET_STAT(found_idle_cpu);
return i;
+ }
+
+ SET_STAT(nofound_idle_cpu);
/*
* For cluster machines which have lower sharing cache like L2 or
@@ -8580,6 +8610,7 @@ static int
select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
{
int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
+ unsigned long time;
struct sched_domain *tmp, *sd = NULL;
int cpu = smp_processor_id();
int new_cpu = prev_cpu;
@@ -8587,6 +8618,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
/* SD_flags and WF_flags share the first nibble */
int sd_flag = wake_flags & 0xF;
+ time = schedstat_start_time();
+
/*
* required for stable ->cpus_allowed
*/
@@ -8643,6 +8676,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags)
}
rcu_read_unlock();
+ schedstat_end_time(cpu_rq(cpu)->find_time, time);
+
return new_cpu;
}
@@ -8981,6 +9016,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
struct sched_entity *se;
struct task_struct *p;
int new_tasks;
+ unsigned long time;
again:
p = pick_task_fair(rq, rf);
@@ -9038,6 +9074,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
idle:
if (rf) {
+ time = schedstat_start_time();
/*
* We must set idle_stamp _before_ calling try_steal() or
* sched_balance_newidle(), such that we measure the duration
@@ -9052,6 +9089,8 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
if (new_tasks)
rq_idle_stamp_clear(rq);
+ schedstat_end_time(rq->find_time, time);
+
/*
* Because try_steal() and sched_balance_newidle() release
* (and re-acquire) rq->lock, it is possible for any higher priority
@@ -13215,6 +13254,7 @@ static int steal_from(struct rq *dst_rq, struct rq_flags *dst_rf, bool *locked,
update_rq_clock(dst_rq);
attach_task(dst_rq, p);
stolen = 1;
+ schedstat_inc(dst_rq->steal);
}
local_irq_restore(rf.flags);
@@ -13239,6 +13279,7 @@ static int try_steal(struct rq *dst_rq, struct rq_flags *dst_rf)
int dst_cpu = dst_rq->cpu;
bool locked = true;
int stolen = 0;
+ bool any_overload = false;
struct sparsemask *overload_cpus;
if (!sched_feat(STEAL))
@@ -13281,6 +13322,7 @@ static int try_steal(struct rq *dst_rq, struct rq_flags *dst_rf)
stolen = 1;
goto out;
}
+ any_overload = true;
}
out:
@@ -13292,6 +13334,8 @@ static int try_steal(struct rq *dst_rq, struct rq_flags *dst_rf)
stolen |= (dst_rq->cfs.h_nr_runnable > 0);
if (dst_rq->nr_running != dst_rq->cfs.h_nr_runnable)
stolen = -1;
+ if (!stolen && any_overload)
+ schedstat_inc(dst_rq->steal_fail);
return stolen;
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4989a92eeb9b..530b80fbf897 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1304,6 +1304,15 @@ struct rq {
/* try_to_wake_up() stats */
unsigned int ttwu_count;
unsigned int ttwu_local;
+
+ /* Idle search stats */
+ unsigned int found_idle_cpu_capacity;
+ unsigned int found_idle_cpu;
+ unsigned int found_idle_cpu_easy;
+ unsigned int nofound_idle_cpu;
+ unsigned long find_time;
+ unsigned int steal;
+ unsigned int steal_fail;
#endif
#ifdef CONFIG_CPU_IDLE
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index d1c9429a4ac5..7063c9712f68 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -129,6 +129,15 @@ static int show_schedstat(struct seq_file *seq, void *v)
rq->rq_cpu_time,
rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
+ seq_printf(seq, " %u %u %u %u %lu %u %u",
+ rq->found_idle_cpu_easy,
+ rq->found_idle_cpu_capacity,
+ rq->found_idle_cpu,
+ rq->nofound_idle_cpu,
+ rq->find_time,
+ rq->steal,
+ rq->steal_fail);
+
seq_printf(seq, "\n");
/* domain-specific stats */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index a612cf253c87..55f31a4df8fa 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -43,6 +43,17 @@ rq_sched_info_dequeue(struct rq *rq, unsigned long long delta)
#define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0)
#define schedstat_val(var) (var)
#define schedstat_val_or_zero(var) ((schedstat_enabled()) ? (var) : 0)
+#define schedstat_start_time() schedstat_val_or_zero(local_clock())
+#define schedstat_end_time(stat, time) \
+ do { \
+ unsigned long endtime; \
+ \
+ if (schedstat_enabled() && (time)) { \
+ endtime = local_clock() - (time) - schedstat_skid; \
+ schedstat_add((stat), endtime); \
+ } \
+ } while (0)
+extern unsigned long schedstat_skid;
void __update_stats_wait_start(struct rq *rq, struct task_struct *p,
struct sched_statistics *stats);
@@ -81,6 +92,8 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt
# define schedstat_set(var, val) do { } while (0)
# define schedstat_val(var) 0
# define schedstat_val_or_zero(var) 0
+# define schedstat_start_time() 0
+# define schedstat_end_time(stat, t) do { } while (0)
# define __update_stats_wait_start(rq, p, stats) do { } while (0)
# define __update_stats_wait_end(rq, p, stats) do { } while (0)
--
2.34.1