In /proc/schedstat, lb_imbalance reports the sum of imbalances
discovered in sched domains with each call to sched_balance_rq(), which is
not very useful because lb_imbalance does not mention whether the imbalance
is due to load, utilization, nr_tasks or misfit_tasks. Remove this field
from /proc/schedstat.

Currently there is no field in /proc/schedstat to report different types
of imbalances. Introduce new fields in /proc/schedstat to report the
total imbalances in load, utilization, nr_tasks or misfit_tasks.

Added fields to /proc/schedstat:
        - lb_imbalance_load: Total imbalance due to load.
        - lb_imbalance_util: Total imbalance due to utilization.
        - lb_imbalance_task: Total imbalance due to number of tasks.
        - lb_imbalance_misfit: Total imbalance due to misfit tasks.

Reviewed-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
---
 include/linux/sched/topology.h |  5 ++++-
 kernel/sched/fair.c            | 21 ++++++++++++++++++++-
 kernel/sched/stats.c           |  7 +++++--
 3 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 4237daa5ac7a..76a662e1ec24 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -114,7 +114,10 @@ struct sched_domain {
 	unsigned int lb_count[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_failed[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_balanced[CPU_MAX_IDLE_TYPES];
-	unsigned int lb_imbalance[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_load[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_util[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_task[CPU_MAX_IDLE_TYPES];
+	unsigned int lb_imbalance_misfit[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_gained[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_hot_gained[CPU_MAX_IDLE_TYPES];
 	unsigned int lb_nobusyg[CPU_MAX_IDLE_TYPES];
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ec403e81ffef..91f33cb9fb23 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11659,6 +11659,25 @@ static int should_we_balance(struct lb_env *env)
 	return group_balance_cpu(sg) == env->dst_cpu;
 }
 
+static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd,
+				     enum cpu_idle_type idle)
+{
+	switch (env->migration_type) {
+	case migrate_load:
+		schedstat_add(sd->lb_imbalance_load[idle], env->imbalance);
+		break;
+	case migrate_util:
+		schedstat_add(sd->lb_imbalance_util[idle], env->imbalance);
+		break;
+	case migrate_task:
+		schedstat_add(sd->lb_imbalance_task[idle], env->imbalance);
+		break;
+	case migrate_misfit:
+		schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
+		break;
+	}
+}
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
@@ -11709,7 +11728,7 @@ static int sched_balance_rq(int this_cpu, struct rq *this_rq,
 
 	WARN_ON_ONCE(busiest == env.dst_rq);
 
-	schedstat_add(sd->lb_imbalance[idle], env.imbalance);
+	update_lb_imbalance_stat(&env, sd, idle);
 
 	env.src_cpu = busiest->cpu;
 	env.src_rq = busiest;
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index eb0cdcd4d921..802bd9398a2e 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -141,11 +141,14 @@ static int show_schedstat(struct seq_file *seq, void *v)
 			seq_printf(seq, "domain%d %*pb", dcount++,
 				   cpumask_pr_args(sched_domain_span(sd)));
 			for (itype = 0; itype < CPU_MAX_IDLE_TYPES; itype++) {
-				seq_printf(seq, " %u %u %u %u %u %u %u %u",
+				seq_printf(seq, " %u %u %u %u %u %u %u %u %u %u %u",
 				    sd->lb_count[itype],
 				    sd->lb_balanced[itype],
 				    sd->lb_failed[itype],
-				    sd->lb_imbalance[itype],
+				    sd->lb_imbalance_load[itype],
+				    sd->lb_imbalance_util[itype],
+				    sd->lb_imbalance_task[itype],
+				    sd->lb_imbalance_misfit[itype],
 				    sd->lb_gained[itype],
 				    sd->lb_hot_gained[itype],
 				    sd->lb_nobusyq[itype],
-- 
2.43.0

On Wed, Dec 18, 2024 at 04:36:26AM +0000, Swapnil Sapkal wrote:

> +static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd,
> +				     enum cpu_idle_type idle)
> +{
> +	switch (env->migration_type) {
> +	case migrate_load:
> +		schedstat_add(sd->lb_imbalance_load[idle], env->imbalance);
> +		break;
> +	case migrate_util:
> +		schedstat_add(sd->lb_imbalance_util[idle], env->imbalance);
> +		break;
> +	case migrate_task:
> +		schedstat_add(sd->lb_imbalance_task[idle], env->imbalance);
> +		break;
> +	case migrate_misfit:
> +		schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
> +		break;
> +	}
> +}


Can you please write that like:

	if (!schedstat_enabled())
		return;

	switch () {
	case ...
		__schedstat_add();
	}

It makes no sense to have 4 copies of schedstat_enabled() inside the
switch statement -- esp. since afaik the compilers aren't able to CSE
static keys :/

Hello Peter,

Thanks for the review.

On 12/18/2024 5:10 PM, Peter Zijlstra wrote:
> On Wed, Dec 18, 2024 at 04:36:26AM +0000, Swapnil Sapkal wrote:
> 
>> +static void update_lb_imbalance_stat(struct lb_env *env, struct sched_domain *sd,
>> +				     enum cpu_idle_type idle)
>> +{
>> +	switch (env->migration_type) {
>> +	case migrate_load:
>> +		schedstat_add(sd->lb_imbalance_load[idle], env->imbalance);
>> +		break;
>> +	case migrate_util:
>> +		schedstat_add(sd->lb_imbalance_util[idle], env->imbalance);
>> +		break;
>> +	case migrate_task:
>> +		schedstat_add(sd->lb_imbalance_task[idle], env->imbalance);
>> +		break;
>> +	case migrate_misfit:
>> +		schedstat_add(sd->lb_imbalance_misfit[idle], env->imbalance);
>> +		break;
>> +	}
>> +}
> 
> 
> Can you please write that like:
> 
> 	if (!schedstat_enabled())
> 		return;
> 
> 	switch () {
> 	case ...
> 		__schedstat_add();
> 	}
> 
> It makes no sense to have 4 copies of schedstat_enabled() inside the
> switch statement -- esp. since afaik the compilers aren't able to CSE
> static keys :/

This makes sense. I will update this change in v2.

--
Thanks and Regards,
Swapnil