Commit-ID: 6833dbedc680daac32418f919e675d208eb45fa9
Gitweb: http://git.kernel.org/tip/6833dbedc680daac32418f919e675d208eb45fa9
Author: Mike Galbraith <[email protected]>
AuthorDate: Mon, 5 Dec 2011 10:01:47 +0100
Committer: Thomas Gleixner <[email protected]>
CommitDate: Fri, 21 Feb 2014 21:43:21 +0100
sched, nohz: Isolated cores do not load balance
The user explicitly disabled load balancing, else this core would not be
disconnected. Don't add these to nohz.idle_cpus_mask.
Cc: Lei Wen <[email protected]>
Signed-off-by: Mike Galbraith <[email protected]>
Signed-off-by: Peter Zijlstra <[email protected]>
Link: http://lkml.kernel.org/n/[email protected]
Signed-off-by: Thomas Gleixner <[email protected]>
---
kernel/sched/fair.c | 25 ++++++++++++++++++-------
1 file changed, 18 insertions(+), 7 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 37ee473..9ca5d57 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6802,6 +6802,11 @@ out_unlock:
return 0;
}
+static inline int on_null_domain(struct rq *rq)
+{
+ return unlikely(!rcu_dereference_sched(rq->sd));
+}
+
#ifdef CONFIG_NO_HZ_COMMON
/*
* idle load balancing details
@@ -6856,8 +6861,13 @@ static void nohz_balancer_kick(void)
static inline void nohz_balance_exit_idle(int cpu)
{
if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
- cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
- atomic_dec(&nohz.nr_cpus);
+ /*
+ * Completely isolated CPUs don't ever set, so we must test.
+ */
+ if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
+ cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
+ atomic_dec(&nohz.nr_cpus);
+ }
clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
}
}
@@ -6911,6 +6921,12 @@ void nohz_balance_enter_idle(int cpu)
if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
return;
+ /*
+ * If we're a completely isolated CPU, we don't play.
+ */
+ if (on_null_domain(cpu_rq(cpu)))
+ return;
+
cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
atomic_inc(&nohz.nr_cpus);
set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
@@ -7173,11 +7189,6 @@ static void run_rebalance_domains(struct softirq_action *h)
nohz_idle_balance(this_rq, idle);
}
-static inline int on_null_domain(struct rq *rq)
-{
- return !rcu_dereference_sched(rq->sd);
-}
-
/*
* Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
*/
On Sun, Feb 23, 2014 at 2:04 AM, tip-bot for Mike Galbraith
<[email protected]> wrote:
> Commit-ID: d987fc7f3228bf94cb6b21313ebab1d64ee637ad
> Gitweb: http://git.kernel.org/tip/d987fc7f3228bf94cb6b21313ebab1d64ee637ad
> Author: Mike Galbraith <[email protected]>
> AuthorDate: Mon, 5 Dec 2011 10:01:47 +0100
> Committer: Ingo Molnar <[email protected]>
> CommitDate: Sat, 22 Feb 2014 18:17:22 +0100
>
> sched, nohz: Exclude isolated cores from load balancing
>
> The user explicitly disabled load balancing, else this core would not be
> disconnected. Don't add these to nohz.idle_cpus_mask.
>
> Signed-off-by: Mike Galbraith <[email protected]>
> Signed-off-by: Peter Zijlstra <[email protected]>
> Cc: Lei Wen <[email protected]>
> Link: http://lkml.kernel.org/n/[email protected]
> Signed-off-by: Thomas Gleixner <[email protected]>
> Signed-off-by: Ingo Molnar <[email protected]>
> ---
> kernel/sched/fair.c | 25 ++++++++++++++++++-------
> 1 file changed, 18 insertions(+), 7 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 7982faf..a3a41c61 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6788,6 +6788,11 @@ out_unlock:
> return 0;
> }
>
> +static inline int on_null_domain(struct rq *rq)
> +{
> + return unlikely(!rcu_dereference_sched(rq->sd));
> +}
> +
> #ifdef CONFIG_NO_HZ_COMMON
> /*
> * idle load balancing details
> @@ -6842,8 +6847,13 @@ static void nohz_balancer_kick(void)
> static inline void nohz_balance_exit_idle(int cpu)
> {
> if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) {
> - cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
> - atomic_dec(&nohz.nr_cpus);
> + /*
> + * Completely isolated CPUs don't ever set, so we must test.
> + */
> + if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) {
> + cpumask_clear_cpu(cpu, nohz.idle_cpus_mask);
How about use the API as cpumask_test_and_clear_cpu?
Then below one line is enough.
+ if (likely(cpumask_test_and_clear_cpu(cpu,
nohz.idle_cpus_mask))) {
And I am not pretty sure whether we need such test here.
Since if one cpu is set to NULL domain, it would not set NOHZ_TICK_STOPPED.
And it would not enter into this logic.
Unless that cpu is set to NULL domain when it already run after
nohz_balance_enter_idle.
Not sure what status would it be, and whether it could be set NULL
domain then...
> + atomic_dec(&nohz.nr_cpus);
> + }
> clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
> }
> }
> @@ -6897,6 +6907,12 @@ void nohz_balance_enter_idle(int cpu)
> if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
> return;
>
> + /*
> + * If we're a completely isolated CPU, we don't play.
> + */
> + if (on_null_domain(cpu_rq(cpu)))
> + return;
> +
Great! it is much better than my previous patch.
> cpumask_set_cpu(cpu, nohz.idle_cpus_mask);
> atomic_inc(&nohz.nr_cpus);
> set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
> @@ -7159,11 +7175,6 @@ static void run_rebalance_domains(struct softirq_action *h)
> nohz_idle_balance(this_rq, idle);
> }
>
> -static inline int on_null_domain(struct rq *rq)
> -{
> - return !rcu_dereference_sched(rq->sd);
> -}
> -
> /*
> * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
> */
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
On Mon, 2014-02-24 at 10:11 +0800, Lei Wen wrote:
> How about use the API as cpumask_test_and_clear_cpu?
> Then below one line is enough.
Yeah.
> + if (likely(cpumask_test_and_clear_cpu(cpu,
> nohz.idle_cpus_mask))) {
>
> And I am not pretty sure whether we need such test here.
It was born because I watched me wreck nohz.nr_cpus :)
-Mike
On Mon, Feb 24, 2014 at 10:11:05AM +0800, Lei Wen wrote:
> How about use the API as cpumask_test_and_clear_cpu?
> Then below one line is enough.
Its more expensive.
On Mon, Feb 24, 2014 at 3:07 PM, Peter Zijlstra <[email protected]> wrote:
> On Mon, Feb 24, 2014 at 10:11:05AM +0800, Lei Wen wrote:
>> How about use the API as cpumask_test_and_clear_cpu?
>> Then below one line is enough.
>
> Its more expensive.
>
I see...
No problem for me then.
Acked-by: Lei Wen <[email protected]>
Thanks,
Lei