Uncouple buddy selection from wakeup granularity. The initial idea was that buddies could run ahead as far as a normal task can - do this by measuring a pair 'slice' just as we do for a normal task. This means we can drop the wakeup_granularity back to 5ms. Signed-off-by: Peter Zijlstra --- kernel/sched.c | 1 + kernel/sched_fair.c | 11 +++++------ 2 files changed, 6 insertions(+), 6 deletions(-) Index: linux-2.6/kernel/sched.c =================================================================== --- linux-2.6.orig/kernel/sched.c 2008-05-12 00:42:40.000000000 +0200 +++ linux-2.6/kernel/sched.c 2008-05-12 00:43:54.000000000 +0200 @@ -370,6 +370,7 @@ u64 exec_clock; u64 min_vruntime; + u64 pair_start; struct rb_root tasks_timeline; struct rb_node *rb_leftmost; Index: linux-2.6/kernel/sched_fair.c =================================================================== --- linux-2.6.orig/kernel/sched_fair.c 2008-05-12 00:42:41.000000000 +0200 +++ linux-2.6/kernel/sched_fair.c 2008-05-12 00:47:05.000000000 +0200 @@ -63,13 +63,13 @@ unsigned int __read_mostly sysctl_sched_ /* * SCHED_OTHER wake-up granularity. - * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds) + * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still * have immediate wakeup/sleep latencies. */ -unsigned int sysctl_sched_wakeup_granularity = 10000000UL; +unsigned int sysctl_sched_wakeup_granularity = 5000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; @@ -787,17 +787,16 @@ se->prev_sum_exec_runtime = se->sum_exec_runtime; } -static int -wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); - static struct sched_entity * pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (!cfs_rq->next) - return se; + struct rq *rq = rq_of(cfs_rq); + u64 pair_slice = rq->clock - cfs_rq->pair_start; - if (wakeup_preempt_entity(cfs_rq->next, se) != 0) + if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) { + cfs_rq->pair_start = rq->clock; return se; + } return cfs_rq->next; } -- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/