Re: [PATCH] sched/fair: Ignore percpu threads for imbalance pulls

2021-02-18 Thread Valentin Schneider
On 17/02/21 14:50, Valentin Schneider wrote: > @@ -7539,6 +7539,9 @@ int can_migrate_task(struct task_struct *p, struct > lb_env *env) > if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) > return 0; > > + if (kthread_is_per_cpu(p)) > + return 0;

Re: [PATCH] sched/fair: Ignore percpu threads for imbalance pulls

2021-02-17 Thread Pavan Kondeti
On Wed, Feb 17, 2021 at 02:50:23PM +, Valentin Schneider wrote: > On 17/02/21 17:38, Lingutla Chandrasekhar wrote: > > In load balancing, when balancing group is unable to pull task > > due to ->cpus_ptr constraints from busy group, then it sets > > LBF_SOME_PINNED to lb env flags, as a

Re: [PATCH] sched/fair: Ignore percpu threads for imbalance pulls

2021-02-17 Thread Valentin Schneider
On 17/02/21 17:38, Lingutla Chandrasekhar wrote: > In load balancing, when balancing group is unable to pull task > due to ->cpus_ptr constraints from busy group, then it sets > LBF_SOME_PINNED to lb env flags, as a consequence, sgc->imbalance > is set for its parent domain level. which makes the

[PATCH] sched/fair: Ignore percpu threads for imbalance pulls

2021-02-17 Thread Lingutla Chandrasekhar
In load balancing, when balancing group is unable to pull task due to ->cpus_ptr constraints from busy group, then it sets LBF_SOME_PINNED to lb env flags, as a consequence, sgc->imbalance is set for its parent domain level. which makes the group classified as imbalance to get help from another