From: Uladzislau Rezki <[email protected]> As a first step this patch makes cfs_tasks list as MRU one. It means, that when a next task is picked to run on physical CPU it is moved to the front of the list.
Therefore, the cfs_tasks list is more or less sorted (except woken tasks) starting from recently given CPU time tasks toward tasks with max wait time in a run-queue, i.e. MRU list. Second, as part of the load balance operation, this approach starts detach_tasks()/detach_one_task() from the tail of the queue instead of the head, giving some advantages: - tends to pick a task with highest wait time; - tasks located in the tail are less likely cache-hot, therefore the can_migrate_task() decision is higher. hackbench illustrates slightly better performance. For example doing 1000 samples and 40 groups on i5-3320M CPU, it shows below figures: default: 0.657 avg patched: 0.646 avg Signed-off-by: Uladzislau Rezki (Sony) <[email protected]> --- kernel/sched/fair.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c77e4b1d51c0..b598907e5236 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6354,10 +6354,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf set_next_entity(cfs_rq, se); } - if (hrtick_enabled(rq)) - hrtick_start_fair(rq, p); - - return p; + goto done; simple: cfs_rq = &rq->cfs; #endif @@ -6375,6 +6372,16 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf p = task_of(se); +done: __maybe_unused +#ifdef CONFIG_SMP + /* + * Move the next running task to the front of + * the list, so our cfs_tasks list becomes MRU + * one. + */ + list_move(&p->se.group_node, &rq->cfs_tasks); +#endif + if (hrtick_enabled(rq)) hrtick_start_fair(rq, p); @@ -6806,11 +6813,12 @@ static void detach_task(struct task_struct *p, struct lb_env *env) */ static struct task_struct *detach_one_task(struct lb_env *env) { - struct task_struct *p, *n; + struct task_struct *p; lockdep_assert_held(&env->src_rq->lock); - list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { + list_for_each_entry_reverse(p, + &env->src_rq->cfs_tasks, se.group_node) { if (!can_migrate_task(p, env)) continue; @@ -6856,7 +6864,7 @@ static int detach_tasks(struct lb_env *env) if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1) break; - p = list_first_entry(tasks, struct task_struct, se.group_node); + p = list_last_entry(tasks, struct task_struct, se.group_node); env->loop++; /* We've more or less seen every task there is, call it quits */ @@ -6906,7 +6914,7 @@ static int detach_tasks(struct lb_env *env) continue; next: - list_move_tail(&p->se.group_node, tasks); + list_move(&p->se.group_node, tasks); } /* -- 2.11.0
