utilization is used to detect a misfit task but the load is then used to select the task on the CPU which can lead to select a small task with high weight instead of the task that triggered the misfit migration.
Signed-off-by: Vincent Guittot <[email protected]> --- kernel/sched/fair.c | 28 ++++++++++++++-------------- kernel/sched/sched.h | 2 +- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 53e64a7..d08cc12 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3817,16 +3817,16 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) return; if (!p) { - rq->misfit_task_load = 0; + rq->misfit_task_util = 0; return; } if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) { - rq->misfit_task_load = 0; + rq->misfit_task_util = 0; return; } - rq->misfit_task_load = task_h_load(p); + rq->misfit_task_util = task_util_est(p); } #else /* CONFIG_SMP */ @@ -7487,14 +7487,14 @@ static int detach_tasks(struct lb_env *env) break; case migrate_misfit: - load = task_h_load(p); + util = task_util_est(p); /* * utilization of misfit task might decrease a bit * since it has been recorded. Be conservative in the * condition. */ - if (load < env->imbalance) + if (2*util < env->imbalance) goto next; env->imbalance = 0; @@ -7785,7 +7785,7 @@ struct sg_lb_stats { unsigned int group_weight; enum group_type group_type; unsigned int group_asym_capacity; /* tasks should be move to preferred cpu */ - unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */ + unsigned long group_misfit_task_util; /* A CPU has a task too big for its capacity */ #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -7959,7 +7959,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) */ static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) { - return rq->misfit_task_load && + return rq->misfit_task_util && (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity || check_cpu_capacity(rq, sd)); } @@ -8078,7 +8078,7 @@ group_type group_classify(struct lb_env *env, if (sgs->group_asym_capacity) return group_asym_capacity; - if (sgs->group_misfit_task_load) + if (sgs->group_misfit_task_util) return group_misfit_task; if (!group_has_capacity(env, sgs)) @@ -8164,8 +8164,8 @@ static inline void update_sg_lb_stats(struct lb_env *env, /* Check for a misfit task on the cpu */ if (env->sd->flags & SD_ASYM_CPUCAPACITY && - sgs->group_misfit_task_load < rq->misfit_task_load) { - sgs->group_misfit_task_load = rq->misfit_task_load; + sgs->group_misfit_task_util < rq->misfit_task_util) { + sgs->group_misfit_task_util = rq->misfit_task_util; *sg_status |= SG_OVERLOAD; } } @@ -8261,7 +8261,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, * If we have more than one misfit sg go with the * biggest misfit. */ - if (sgs->group_misfit_task_load < busiest->group_misfit_task_load) + if (sgs->group_misfit_task_util < busiest->group_misfit_task_util) return false; break; @@ -8458,7 +8458,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s if (busiest->group_type == group_misfit_task) { /* Set imbalance to allow misfit task to be balanced. */ env->balance_type = migrate_misfit; - env->imbalance = busiest->group_misfit_task_load; + env->imbalance = busiest->group_misfit_task_util; return; } @@ -8801,8 +8801,8 @@ static struct rq *find_busiest_queue(struct lb_env *env, * For ASYM_CPUCAPACITY domains with misfit tasks we simply * seek the "biggest" misfit task. */ - if (rq->misfit_task_load > busiest_load) { - busiest_load = rq->misfit_task_load; + if (rq->misfit_task_util > busiest_util) { + busiest_util = rq->misfit_task_util; busiest = rq; } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 7583fad..ef6e1b2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -916,7 +916,7 @@ struct rq { unsigned char idle_balance; - unsigned long misfit_task_load; + unsigned long misfit_task_util; /* For active balancing */ int active_balance; -- 2.7.4
