sched: minor fast-path overhead reduction
Greetings,
103638d added a bit of avoidable overhead to the fast-path.
Use sysctl_sched_min_granularity instead of sched_slice() to restrict buddy wakeups.
Signed-off-by Mike Galbraith <[email protected]>
kernel/sched_fair.c +1 -1
@@ -747,7 +747,7 @@ pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)struct rq *rq =rq_of (cfs_rq);u64 pair_slice = rq->clock - cfs_rq->pair_start; -if (!cfs_rq->next || pair_slice >sched_slice (cfs_rq, cfs_rq->next)) { +if (!cfs_rq->next || pair_slice > sysctl_sched_min_granularity) { cfs_rq->pair_start = rq->clock;return se; }
Ingo Molnar
AppliedQuoted 7 lines · Mike Galbraith
Greetings,
103638d added a bit of avoidable overhead to the fast-path.
Use
sysctl_sched_min_granularityinstead ofsched_slice()to restrict buddy wakeups.Signed-off-by Mike Galbraith <[email protected]>
applied to tip/sched/urgent, thanks Mike!
Ingo