Re: [PATCH tip/core/rcu 11/17] rcu: Bind grace-period kthreads to non-NO_HZ_FULL CPUs

[Frederic Weisbecker <fweisbec@gmail.com>]

On Mon, Jul 07, 2014 at 03:38:15PM -0700, Paul E. McKenney wrote:
> From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
> 
> Binding the grace-period kthreads to the timekeeping CPU resulted in
> significant performance decreases for some workloads.  For more detail,
> see:
> 
> https://lkml.org/lkml/2014/6/3/395 for benchmark numbers
> 
> https://lkml.org/lkml/2014/6/4/218 for CPU statistics
> 
> It turns out that it is necessary to bind the grace-period kthreads
> to the timekeeping CPU only when all but CPU 0 is a nohz_full CPU
> on the one hand or if CONFIG_NO_HZ_FULL_SYSIDLE=y on the other.
> In other cases, it suffices to bind the grace-period kthreads to the
> set of non-nohz_full CPUs.
> 
> This commit therefore creates a tick_nohz_not_full_mask that is the
> complement of tick_nohz_full_mask, and then binds the grace-period
> kthread to the set of CPUs indicated by this new mask, which covers
> the CONFIG_NO_HZ_FULL_SYSIDLE=n case.  The CONFIG_NO_HZ_FULL_SYSIDLE=y
> case still binds the grace-period kthreads to the timekeeping CPU.
> This commit also includes the tick_nohz_full_enabled() check suggested
> by Frederic Weisbecker.
> 
> Reported-by: Jet Chen <jet.chen@intel.com>
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> [ paulmck: Created housekeeping_affine() per fweisbec feedback. ]
> ---
>  include/linux/tick.h     | 19 +++++++++++++++++++
>  kernel/rcu/tree_plugin.h | 14 +++++++++-----
>  kernel/time/tick-sched.c | 10 ++++++++++
>  3 files changed, 38 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/tick.h b/include/linux/tick.h
> index b84773cb9f4c..c39af3261351 100644
> --- a/include/linux/tick.h
> +++ b/include/linux/tick.h
> @@ -12,6 +12,7 @@
>  #include <linux/hrtimer.h>
>  #include <linux/context_tracking_state.h>
>  #include <linux/cpumask.h>
> +#include <linux/sched.h>
>  
>  #ifdef CONFIG_GENERIC_CLOCKEVENTS
>  
> @@ -162,6 +163,7 @@ static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
>  #ifdef CONFIG_NO_HZ_FULL
>  extern bool tick_nohz_full_running;
>  extern cpumask_var_t tick_nohz_full_mask;
> +extern cpumask_var_t tick_nohz_not_full_mask;

So I'm still puzzled by this mask.

How about creating a temporary cpumask on top of tick_nohz_full_mask
from housekeeping_affine().

If you wonder about performance, this can be called once for good from
rcu_spawn_gp_kthread() (that would be much better than checking that all
the time from the kthread itself anyway).

In case you're out of time, I can handle that. Just checking your opinion.

Thanks.

>  
>  static inline bool tick_nohz_full_enabled(void)
>  {
> @@ -194,6 +196,23 @@ static inline void tick_nohz_full_kick_all(void) { }
>  static inline void __tick_nohz_task_switch(struct task_struct *tsk) { }
>  #endif
>  
> +static inline bool is_housekeeping_cpu(int cpu)
> +{
> +#ifdef CONFIG_NO_HZ_FULL
> +	if (tick_nohz_full_enabled())
> +		return cpumask_test_cpu(cpu, tick_nohz_not_full_mask);
> +#endif
> +	return true;
> +}
> +
> +static inline void housekeeping_affine(struct task_struct *t)
> +{
> +#ifdef CONFIG_NO_HZ_FULL
> +	if (tick_nohz_full_enabled())
> +		set_cpus_allowed_ptr(t, tick_nohz_not_full_mask);
> +#endif
> +}
> +
>  static inline void tick_nohz_full_check(void)
>  {
>  	if (tick_nohz_full_enabled())
> diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
> index 719587af7b10..b39ba7239bd6 100644
> --- a/kernel/rcu/tree_plugin.h
> +++ b/kernel/rcu/tree_plugin.h
> @@ -2846,12 +2846,16 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
>   */
>  static void rcu_bind_gp_kthread(void)
>  {
> -#ifdef CONFIG_NO_HZ_FULL
> -	int cpu = tick_do_timer_cpu;
> +	int __maybe_unused cpu;
>  
> -	if (cpu < 0 || cpu >= nr_cpu_ids)
> +	if (!tick_nohz_full_enabled())
>  		return;
> -	if (raw_smp_processor_id() != cpu)
> +#ifdef CONFIG_NO_HZ_FULL_SYSIDLE
> +	cpu = tick_do_timer_cpu;
> +	if (cpu >= 0 && cpu < nr_cpu_ids && raw_smp_processor_id() != cpu)
>  		set_cpus_allowed_ptr(current, cpumask_of(cpu));
> -#endif /* #ifdef CONFIG_NO_HZ_FULL */
> +#else /* #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
> +	if (!is_housekeeping_cpu(raw_smp_processor_id()))
> +		housekeeping_affine(current);
> +#endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */
>  }
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index 6558b7ac112d..e023134d63a1 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -154,6 +154,7 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
>  
>  #ifdef CONFIG_NO_HZ_FULL
>  cpumask_var_t tick_nohz_full_mask;
> +cpumask_var_t tick_nohz_not_full_mask;
>  bool tick_nohz_full_running;
>  
>  static bool can_stop_full_tick(void)
> @@ -281,6 +282,7 @@ static int __init tick_nohz_full_setup(char *str)
>  	int cpu;
>  
>  	alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
> +	alloc_bootmem_cpumask_var(&tick_nohz_not_full_mask);
>  	if (cpulist_parse(str, tick_nohz_full_mask) < 0) {
>  		pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
>  		return 1;
> @@ -291,6 +293,8 @@ static int __init tick_nohz_full_setup(char *str)
>  		pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
>  		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
>  	}
> +	cpumask_andnot(tick_nohz_not_full_mask,
> +		       cpu_possible_mask, tick_nohz_full_mask);
>  	tick_nohz_full_running = true;
>  
>  	return 1;
> @@ -332,9 +336,15 @@ static int tick_nohz_init_all(void)
>  		pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
>  		return err;
>  	}
> +	if (!alloc_cpumask_var(&tick_nohz_not_full_mask, GFP_KERNEL)) {
> +		pr_err("NO_HZ: Can't allocate not-full dynticks cpumask\n");
> +		return err;
> +	}
>  	err = 0;
>  	cpumask_setall(tick_nohz_full_mask);
>  	cpumask_clear_cpu(smp_processor_id(), tick_nohz_full_mask);
> +	cpumask_clear(tick_nohz_not_full_mask);
> +	cpumask_set_cpu(smp_processor_id(), tick_nohz_not_full_mask);
>  	tick_nohz_full_running = true;
>  #endif
>  	return err;
> -- 
> 1.8.1.5
>