From eae0c9dfb534cb3449888b9601228efa6480fdb5 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Tue, 10 Nov 2009 03:50:02 +0100 Subject: [PATCH] sched: Fix and clean up rate-limit newidle code Commit 1b9508f, "Rate-limit newidle" has been confirmed to fix the netperf UDP loopback regression reported by Alex Shi. This is a cleanup and a fix: - moved to a more out of the way spot - fix to ensure that balancing doesn't try to balance runqueues which haven't gone online yet, which can mess up CPU enumeration during boot. Reported-by: Alex Shi Reported-by: Zhang, Yanmin Signed-off-by: Mike Galbraith Acked-by: Peter Zijlstra Cc: # .32.x: a1f84a3: sched: Check for an idle shared cache Cc: # .32.x: 1b9508f: sched: Rate-limit newidle Cc: # .32.x: fd21073: sched: Fix affinity logic Cc: # .32.x LKML-Reference: <1257821402.5648.17.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-) diff --git a/kernel/sched.c b/kernel/sched.c index 23e353568d8e..ad37776cc39b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2354,17 +2354,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, if (rq != orig_rq) update_rq_clock(rq); - if (rq->idle_stamp) { - u64 delta = rq->clock - rq->idle_stamp; - u64 max = 2*sysctl_sched_migration_cost; - - if (delta > max) - rq->avg_idle = max; - else - update_avg(&rq->avg_idle, delta); - rq->idle_stamp = 0; - } - WARN_ON(p->state != TASK_WAKING); cpu = task_cpu(p); @@ -2421,6 +2410,17 @@ out_running: #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) p->sched_class->task_wake_up(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } #endif out: task_rq_unlock(rq, &flags); @@ -4098,7 +4098,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, unsigned long flags; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_online_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -4261,7 +4261,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) int all_pinned = 0; struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - cpumask_setall(cpus); + cpumask_copy(cpus, cpu_online_mask); /* * When power savings policy is enabled for the parent domain, idle @@ -9522,6 +9522,8 @@ void __init sched_init(void) rq->cpu = i; rq->online = 0; rq->migration_thread = NULL; + rq->idle_stamp = 0; + rq->avg_idle = 2*sysctl_sched_migration_cost; INIT_LIST_HEAD(&rq->migration_queue); rq_attach_root(rq, &def_root_domain); #endif -- 2.39.5