Re: [PATCH v3 17/20] sched/core: Introduce default arch handling code for inc/dec preferred CPUs

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

On 6/9/26 12:10 AM, Ilya Leoshkevich wrote:
> 
> 
> On 5/14/26 17:22, Shrikanth Hegde wrote:
>> Define default handlers for high/low steal time. If arch has better
>> decision logic, may override the default implementation.
>>
>> - If the steal time higher than threshold, reduce the number of preferred
>>    CPUs by 1 core. The last core in the intersection of online and
>>    preferred CPUs will be marked as non-preferred.
>>    Ensure at least one core is left as preferred always.
>>
>> - If the steal time lower than threshold, increase the number of 
>> preferred
>>    CPUs by 1 core. First online core which is not in 
>> cpu_preferred_mask will
>>    be marked as preferred.
>>    If all cores are already set to preferred, bail out.
>>
>> Increase/Decrease may need to modify the splicing across NUMA nodes. 
>> It is
>> being kept simple for now.
>>
>> Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
>> ---
>>   include/linux/sched.h |  2 ++
>>   kernel/sched/core.c   | 58 +++++++++++++++++++++++++++++++++++++++++++
>>   2 files changed, 60 insertions(+)
> 
> [...]
> 
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index a3f65e9c7d30..195e3648b1b5 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -11368,6 +11368,64 @@ void sched_init_steal_monitor(void)
>>       steal_mon.sampling_period_ms  = 1000;        /* once per second */
>>   }
>> +/*
>> + * Default implementation of decrementing the preferred CPUs based on 
>> steal
>> + * time. This is simple logic and decrease the preferred CPUs by 1 core.
>> + * It takes out the last core in the online & preferred.
>> + *
>> + * Ensure at least one housekeeping core is always kept as preferred
>> + *
>> + * Could be overwritten by arch specific handling.
>> + */
>> +#ifndef arch_dec_preferred_cpus
>> +void arch_dec_preferred_cpus(struct steal_monitor_t *sm, u64 
>> steal_ratio)
>> +{
>> +    int last_cpu, tmp_cpu;
>> +    int this_cpu = raw_smp_processor_id();
>> +
>> +    cpumask_and(sm->tmp_mask, cpu_online_mask, cpu_preferred_mask);
> 
> Since preferred is always a subset of online, do we even need this?
> Dropping tmp_mask will also make the error handling concern I posted
> earlier go away.
> 

You are right. Decrement doesn't need this. Thanks for catching this.

I ran through the cases mentioned here and some more. I don't see a good reason
to have the tmp_mask.
https://lore.kernel.org/all/0d8412de-e18a-476f-9eb6-9a977f4474a3@linux.ibm.com/