Re: [PATCH v4 14/20] sched/core: Introduce a simple steal monitor

[Shrikanth Hegde <sshegde@linux.ibm.com>]

On 6/18/26 10:00 AM, Yury Norov wrote:
> On Wed, Jun 17, 2026 at 11:11:33PM +0530, Shrikanth Hegde wrote:
>> Start with a simple steal monitor.
>>
>> It is meant to look at steal time and make the decision to
>> reduce/increase the preferred CPUs.
>>
>> It has
>> - work function to execute the steal time calculations and decision
>>    making periodically.
>> - low and high thresholds for steal time.
>> - sampling period to control the frequency of steal time calculations.
>> - cache the previous decision to avoid oscillations
> 
> This monitor is the one implementation out of quite many possible,
> right? I don't think it should live in the core scheduler files, it
> should be a module.

You mean similar to drivers/cpuidle/? a new one drivers/steal_monitor/ ?

>   
>> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
>> ---
>> v3->v4:
>> - Drop tmp_mask
>>
>>   include/linux/sched.h | 11 +++++++++++
>>   kernel/sched/core.c   | 23 +++++++++++++++++++++++
>>   kernel/sched/sched.h  |  3 +++
>>   3 files changed, 37 insertions(+)
>>
>> diff --git a/include/linux/sched.h b/include/linux/sched.h
>> index 5f523782ca28..ce6bc8a22eb1 100644
>> --- a/include/linux/sched.h
>> +++ b/include/linux/sched.h
>> @@ -2517,4 +2517,15 @@ extern void migrate_enable(void);
>>   
>>   DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
>>   
>> +#ifdef CONFIG_PREFERRED_CPU
>> +struct steal_monitor_t {
>> +	struct work_struct  work;
>> +	ktime_t prev_time;
>> +	u64 prev_steal;
>> +	int previous_decision;
>> +	unsigned int low_threshold;
>> +	unsigned int high_threshold;
>> +	unsigned int sampling_period_ms;
>> +};
>> +#endif
>>   #endif
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index 24d4abc74241..cc48632dd42d 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -9138,6 +9138,8 @@ void __init sched_init(void)
>>   
>>   	preempt_dynamic_init();
>>   
>> +	sched_init_steal_monitor();
>> +
>>   	scheduler_running = 1;
>>   }
>>   
>> @@ -11384,4 +11386,25 @@ void sched_push_current_non_preferred_cpu(struct rq *rq)
>>   	stop_one_cpu_nowait(rq->cpu, sched_non_preferred_cpu_push_stop,
>>   			    push_task, this_cpu_ptr(&npc_push_task_work));
>>   }
>> +
>> +struct steal_monitor_t steal_mon;
>> +
>> +void sched_init_steal_monitor(void)
>> +{
>> +	INIT_WORK(&steal_mon.work, sched_steal_detection_work);
>> +	steal_mon.low_threshold       = 200;		/* 2% steal time */
>> +	steal_mon.high_threshold      = 500;		/* 5% steal time */
>> +	steal_mon.sampling_period_ms  = 1000;		/* once per second */
>> +}
>> +
>> +/* This is only a skeleton. Subsequent patches introduce more of it */
>> +void sched_steal_detection_work(struct work_struct *work)
>> +{
>> +	struct steal_monitor_t *sm = container_of(work, struct steal_monitor_t, work);
>> +	ktime_t now;
>> +
>> +	/* Update the prev_time for next iteration*/
>> +	now = ktime_get();
>> +	sm->prev_time = now;
>> +}
>>   #endif
>> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
>> index 9cb006c21090..984da3827f19 100644
>> --- a/kernel/sched/sched.h
>> +++ b/kernel/sched/sched.h
>> @@ -4240,8 +4240,11 @@ static inline bool task_has_preferred_cpus(struct task_struct *p)
>>   #ifdef CONFIG_PREFERRED_CPU
>>   DECLARE_STATIC_KEY_FALSE(__sched_sm_enable);
>>   
>> +void sched_init_steal_monitor(void);
>> +void sched_steal_detection_work(struct work_struct *work);
>>   void sched_push_current_non_preferred_cpu(struct rq *rq);
>>   #else	/* !CONFIG_PREFERRED_CPU */
>>   static inline void sched_push_current_non_preferred_cpu(struct rq *rq) { }
>> +static inline void sched_init_steal_monitor(void) { }
>>   #endif
>>   #endif /* _KERNEL_SCHED_SCHED_H */
>> -- 
>> 2.47.3