From df1c99d416500da8d26a4d78777467c53ee7689e Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 10 Mar 2009 19:08:11 +0100 Subject: [PATCH] sched: add avg_overlap decay Impact: more precise avg_overlap metric - better load-balancing avg_overlap is used to measure the runtime overlap of the waker and wakee. However, when a process changes behaviour, eg a pipe becomes un-congested and we don't need to go to sleep after a wakeup for a while, the avg_overlap value grows stale. When running we use the avg runtime between preemption as a measure for avg_overlap since the amount of runtime can be correlated to cache footprint. The longer we run, the less likely we'll be wanting to be migrated to another CPU. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1236709131.25234.576.camel@laptop> Signed-off-by: Ingo Molnar --- kernel/sched.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/kernel/sched.c b/kernel/sched.c index af5cd1b2d03e..2f28351892c9 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4620,6 +4620,28 @@ static inline void schedule_debug(struct task_struct *prev) #endif } +static void put_prev_task(struct rq *rq, struct task_struct *prev) +{ + if (prev->state == TASK_RUNNING) { + u64 runtime = prev->se.sum_exec_runtime; + + runtime -= prev->se.prev_sum_exec_runtime; + runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); + + /* + * In order to avoid avg_overlap growing stale when we are + * indeed overlapping and hence not getting put to sleep, grow + * the avg_overlap on preemption. + * + * We use the average preemption runtime because that + * correlates to the amount of cache footprint a task can + * build up. + */ + update_avg(&prev->se.avg_overlap, runtime); + } + prev->sched_class->put_prev_task(rq, prev); +} + /* * Pick up the highest-prio task: */ @@ -4698,7 +4720,7 @@ need_resched_nonpreemptible: if (unlikely(!rq->nr_running)) idle_balance(cpu, rq); - prev->sched_class->put_prev_task(rq, prev); + put_prev_task(rq, prev); next = pick_next_task(rq); if (likely(prev != next)) { -- 2.11.0