Prev: cfq: always return false from should_idle if slice_idle is set to zero
Next: MMC: fix all hangs related to mmc/sd card insert/removal during suspend/resume.
From: Andrew Morton on 21 Jun 2010 16:20
On Thu, 17 Jun 2010 16:56:32 -0700
Tim Chen <tim.c.chen(a)linux.intel.com> wrote:

> Add percpu_counter_compare that allows for a quick but accurate
> comparison of percpu_counter with a given value.
>
> A rough count is provided by the count field in percpu_counter structure,
> without accounting for the other values stored in individual cpu counters.
> The actual count is a sum of count and the cpu counters. However, count field is
> never different from the actual value by a factor of batch*num_online_cpu.
> We do not need to get actual count for comparison if count
> is different from the given value by this factor and allows for
> quick comparison without summing up all the per cpu counters.
>
> Signed-off-by: Tim Chen <tim.c.chen(a)linux.intel.com>
> include/linux/percpu_counter.h | 11 +++++++++++
> lib/percpu_counter.c | 27 +++++++++++++++++++++++++++
> 2 files changed, 38 insertions(+), 0 deletions(-)
>
> diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
> index c88d67b..8a7d510 100644
> --- a/include/linux/percpu_counter.h
> +++ b/include/linux/percpu_counter.h
> @@ -40,6 +40,7 @@ void percpu_counter_destroy(struct percpu_counter *fbc);
> void percpu_counter_set(struct percpu_counter *fbc, s64 amount);
> void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch);
> s64 __percpu_counter_sum(struct percpu_counter *fbc);
> +int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs);
>
> static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
> {
> @@ -98,6 +99,16 @@ static inline void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
> fbc->count = amount;
> }
>
> +static inline int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
> +{
> + if (fbc->count > rhs)
> + return 1;
> + else if (fbc->count < rhs)
> + return -1;
> + else
> + return 0;
> +}

It'd be nice if this interface were defined as returning a number
less-than, greater-than or equal to zero. Like the qsort() callback.
It's a pretty common idiom. That way, the above code becomes just

return fbc->count - rhs;

However that does require that percpu_counter_compare() return an s64,
which might make the code generated at callers a little less efficient.

I guess it doesn't matter much.

> static inline void
> percpu_counter_add(struct percpu_counter *fbc, s64 amount)
> {
> diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
> index aeaa6d7..ec9048e 100644
> --- a/lib/percpu_counter.c
> +++ b/lib/percpu_counter.c
> @@ -137,6 +137,33 @@ static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
> return NOTIFY_OK;
> }
>
> +/*
> + * Compare counter against given value.
> + * Return 1 if greater, 0 if equal and -1 if less
> + */
> +int percpu_counter_compare(struct percpu_counter *fbc, s64 rhs)
> +{
> + s64 count;
> +
> + count = percpu_counter_read(fbc);
> + /* Check to see if rough count will be sufficient for comparison */
> + if (abs(count - rhs) > (percpu_counter_batch*num_online_cpus())) {
> + if (count > rhs)
> + return 1;
> + else
> + return -1;
> + }
> + /* Need to use precise count */
> + count = percpu_counter_sum(fbc);
> + if (count > rhs)
> + return 1;
> + else if (count < rhs)
> + return -1;
> + else
> + return 0;
> +}
> +EXPORT_SYMBOL(percpu_counter_compare);

Looks OK. For API uniformity we should have a

__percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, int batch)

but that can be added later if needed I guess.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
 | 
Pages: 1
Prev: cfq: always return false from should_idle if slice_idle is set to zero
Next: MMC: fix all hangs related to mmc/sd card insert/removal during suspend/resume.