linux-kernel - Re: [RFC PATCH v2 1/3] sched/fair: introduce new scheduler group type group

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <e2495b3a-81c5-4238-b766-2ab6e892b6bf@linux.ibm.com>
Date: Thu, 20 Feb 2025 11:53:32 +0100
From: Tobias Huschle <huschle@...ux.ibm.com>
To: Shrikanth Hegde <sshegde@...ux.ibm.com>
Cc: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, dietmar.eggemann@....com,
        rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de,
        vschneid@...hat.com, linuxppc-dev@...ts.ozlabs.org,
        linux-s390@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [RFC PATCH v2 1/3] sched/fair: introduce new scheduler group type
 group_parked



On 18/02/2025 06:44, Shrikanth Hegde wrote:
[...]
>> @@ -1352,6 +1352,9 @@ bool sched_can_stop_tick(struct rq *rq)
>>       if (rq->cfs.h_nr_queued > 1)
>>           return false;
>> +    if (rq->cfs.nr_running > 0 && arch_cpu_parked(cpu_of(rq)))
>> +        return false;
>> +
> 
> you mean rq->cfs.h_nr_queued or rq->nr_running ?
> 

cfs.h_nr_queued is probably more sensible, will use that.

[...]
>> @@ -11259,6 +11293,8 @@ static inline void calculate_imbalance(struct 
>> lb_env *env, struct sd_lb_stats *s
>>    * avg_load : Only if imbalance is significant enough.
>>    * nr_idle :  dst_cpu is not busy and the number of idle CPUs is quite
>>    *            different in groups.
>> + * nr_task :  balancing can go either way depending on the number of 
>> running tasks
>> + *            per group
>>    */
> 
> This comment on nr_task can be removed as it is not present in the list.
> 

Consider it gone.

[...]
>> @@ -11766,7 +11822,7 @@ static int sched_balance_rq(int this_cpu, 
>> struct rq *this_rq,
>>       ld_moved = 0;
>>       /* Clear this flag as soon as we find a pullable task */
>>       env.flags |= LBF_ALL_PINNED;
>> -    if (busiest->nr_running > 1) {
>> +    if (busiest->nr_running > 1 || arch_cpu_parked(busiest->cpu)) {
> 
> Since there is reliance on active balance if there is single task, it 
> think above isn't needed. Is there any usecase for it?
>

Seems to work without that check. I have no particular use case in mind.

>>           /*
>>            * Attempt to move tasks. If sched_balance_find_src_group 
>> has found
>>            * an imbalance but busiest->nr_running <= 1, the group is
>> @@ -12356,6 +12412,11 @@ static void nohz_balancer_kick(struct rq *rq)
>>       if (time_before(now, nohz.next_balance))
>>           goto out;
>> +    if (!idle_cpu(rq->cpu)) {
>> +        flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
>> +        goto out;
>> +    }
>> +
> 
> This could be agrressive. Note when the code comes here, it is not idle. 
> It would bail out early if it is idle.
> 

It seems like we can do without this one as well.

>>       if (rq->nr_running >= 2) {
>>           flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK;
>>           goto out;
>> @@ -12767,6 +12828,9 @@ static int sched_balance_newidle(struct rq 
>> *this_rq, struct rq_flags *rf)
>>       update_misfit_status(NULL, this_rq);
>> +    if (arch_cpu_parked(this_cpu))
>> +        return 0;
>> +
>>       /*
>>        * There is a task waiting to run. No need to search for one.
>>        * Return 0; the task will be enqueued when switching to idle.
>> diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
>> index 456d339be98f..7efd76a30be7 100644
>> --- a/kernel/sched/syscalls.c
>> +++ b/kernel/sched/syscalls.c
>> @@ -214,6 +214,9 @@ int idle_cpu(int cpu)
>>           return 0;
>>   #endif
>> +    if (arch_cpu_parked(cpu))
>> +        return 0;
>> +
>>       return 1;
>>   }
>