On Mon, 2012-10-29 at 16:27 -0400, Steven Rostedt wrote:
> #ifdef CONFIG_CPUSETS
>
> @@ -235,4 +236,34 @@ static inline bool put_mems_allowed(unsigned int seq)
>
> #endif /* !CONFIG_CPUSETS */
>
> +#ifdef CONFIG_CPUSETS_NO_HZ
> +
> +DECLARE_PER_CPU(atomic_t, cpu_adaptive_nohz_ref);
> +
> +static inline bool cpuset_cpu_adaptive_nohz(int cpu)
> +{
> + atomic_t *ref = &per_cpu(cpu_adaptive_nohz_ref, cpu);
> +
> + if (atomic_add_return(0, ref) > 0)
I'm assuming you do the atomic_add_return() for the implicit memory
barrier? Yuck!
Please comment this. I see that rcutree.c does the same thing without a
comment. Bad Paul, bad!
> + return true;
> +
> + return false;
> +}
> +
> +static inline bool cpuset_adaptive_nohz(void)
> +{
> + /*
> + * We probably want to do atomic_read() when we read
> + * locally to avoid the overhead of an ordered add.
> + * For that we have to do the dec of the ref locally as
> + * well.
Does it matter if we miss the dec? What other synchronization is used?
CPU 1 CPU 2
------ -----
var = atomic_add_return(0, ref)
atomic_dec(ref);
if (var > 0)
returns true.
For local cases, as this seems to be in a fast path, we should use
this_cpu_read() as well.
> + */
> + return cpuset_cpu_adaptive_nohz(smp_processor_id());
> +}
> +#else
> +static inline bool cpuset_cpu_adaptive_nohz(int cpu) { return false; }
> +static inline bool cpuset_adaptive_nohz(void) { return false; }
> +
> +#endif /* CONFIG_CPUSETS_NO_HZ */
> +
> #endif /* _LINUX_CPUSET_H */
> diff --git a/init/Kconfig b/init/Kconfig
> index 6fdd6e3..ffdeeab 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -749,6 +749,14 @@ config PROC_PID_CPUSET
> depends on CPUSETS
> default y
>
> +config CPUSETS_NO_HZ
> + bool "Tickless cpusets"
> + depends on CPUSETS && HAVE_CPUSETS_NO_HZ
> + help
> + This options let you apply a nohz property to a cpuset such
> + that the periodic timer tick tries to be avoided when possible on
> + the concerned CPUs.
> +
> config CGROUP_CPUACCT
> bool "Simple CPU accounting cgroup subsystem"
> help
> diff --git a/kernel/cpuset.c b/kernel/cpuset.c
> index f33c715..6319d8e 100644
> --- a/kernel/cpuset.c
> +++ b/kernel/cpuset.c
> @@ -145,6 +145,7 @@ typedef enum {
> CS_SCHED_LOAD_BALANCE,
> CS_SPREAD_PAGE,
> CS_SPREAD_SLAB,
> + CS_ADAPTIVE_NOHZ,
> } cpuset_flagbits_t;
>
> /* the type of hotplug event */
> @@ -189,6 +190,11 @@ static inline int is_spread_slab(const struct cpuset *cs)
> return test_bit(CS_SPREAD_SLAB, &cs->flags);
> }
>
> +static inline int is_adaptive_nohz(const struct cpuset *cs)
> +{
> + return test_bit(CS_ADAPTIVE_NOHZ, &cs->flags);
> +}
We can move this into the #ifdef CONFIG_CPUSETS_NO_HZ as well, and have
the #else version just return zero. Why use test_bit() when we already
know the answer?
> +
> static struct cpuset top_cpuset = {
> .flags = ((1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)),
> };
> @@ -1190,6 +1196,32 @@ static void cpuset_change_flag(struct task_struct *tsk,
> cpuset_update_task_spread_flag(cgroup_cs(scan->cg), tsk);
> }
>
> +#ifdef CONFIG_CPUSETS_NO_HZ
> +
> +DEFINE_PER_CPU(atomic_t, cpu_adaptive_nohz_ref);
> +
> +static void update_nohz_cpus(struct cpuset *old_cs, struct cpuset *cs)
> +{
> + int cpu;
> + int val;
> +
> + if (is_adaptive_nohz(old_cs) == is_adaptive_nohz(cs))
> + return;
> +
> + for_each_cpu(cpu, cs->cpus_allowed) {
> + atomic_t *ref = &per_cpu(cpu_adaptive_nohz_ref, cpu);
> + if (is_adaptive_nohz(cs))
> + atomic_inc(ref);
> + else
> + atomic_dec(ref);
> + }
> +}
> +#else
> +static inline void update_nohz_cpus(struct cpuset *old_cs, struct cpuset *cs)
> +{
> +}
> +#endif
> +
-- Steve
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
