[PATCH] sched: Fix and clean up rate-limit newidle code

From: Mike Galbraith
Date: Mon Nov 09 2009 - 21:50:02 EST


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 <alex.shi@xxxxxxxxx>
Reported-by: Zhang, Yanmin <yanmin_zhang@xxxxxxxxxxxxxxx>
Signed-off-by: Mike Galbraith <efault@xxxxxx>
Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: <stable@xxxxxxxxxx> # .32.x: a1f84a3: sched: Check for an idle shared cache
Cc: <stable@xxxxxxxxxx> # .32.x: 1b9508f: sched: Rate-limit newidle
Cc: <stable@xxxxxxxxxx> # .32.x: fd21073: sched: Fix affinity logic
Cc: <stable@xxxxxxxxxx> # .32.x
LKML-Reference: <1257821402.5648.17.camel@xxxxxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
---
kernel/sched.c | 28 +++++++++++++++-------------
1 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 23e3535..ad37776 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

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/