On Mon, Aug 28, 2017 at 10:41:55AM +0200, Peter Zijlstra wrote: > On Fri, Aug 25, 2017 at 12:11:31AM +0200, Uladzislau Rezki (Sony) wrote: > > 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. > > > > Thefore, 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: 0.644 avg > > patched: 0.637 avg > > > > Signed-off-by: Uladzislau Rezki (Sony) <[email protected]> > > --- > > kernel/sched/fair.c | 19 ++++++++++++++----- > > 1 file changed, 14 insertions(+), 5 deletions(-) > > > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c > > index c77e4b1d51c0..cda281c6bb29 100644 > > --- a/kernel/sched/fair.c > > +++ b/kernel/sched/fair.c > > @@ -6357,7 +6357,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct > > *prev, struct rq_flags *rf > > if (hrtick_enabled(rq)) > > hrtick_start_fair(rq, p); > > > > - return p; > > + goto done; > > simple: > > cfs_rq = &rq->cfs; > > #endif > > @@ -6378,6 +6378,14 @@ pick_next_task_fair(struct rq *rq, struct > > task_struct *prev, struct rq_flags *rf > > if (hrtick_enabled(rq)) > > hrtick_start_fair(rq, p); > > > > +done: __maybe_unused > > + /* > > + * Move the next running task to the front of > > + * the list, so our cfs_tasks list becomes MRU > > + * one. > > + */ > > + list_move(&se->group_node, &rq->cfs_tasks); > > + > > return p; > > > > idle: > > Could you also run something like: > > $ taskset 1 perf bench sched pipe > > to make sure the added list_move() doesn't hurt, I'm not sure group_node > and cfs_tasks are in cachelines we already touch for that operation. > > And if you can see that list_move() hurt in "perf annotate", try moving > those members around to lines that we already need anyway. @Peter: just in case if you missed my email. I uploaded one more patch provided where i provided latest result as well. Please have a look at following links:
https://lkml.org/lkml/2017/9/13/167 https://lkml.org/lkml/2017/9/13/168 Best Regards, Uladzislau Rezki
