On Thu 17-09-15 09:09:31, Naoya Horiguchi wrote:
> Currently there's no easy way to get per-process usage of hugetlb pages, which
> is inconvenient because userspace applications which use hugetlb typically want
> to control their processes on the basis of how much memory (including hugetlb)
> they use. So this patch simply provides easy access to the info via
> /proc/PID/status.
Thank you for making this much more lightweight. If we ever have a
request for a per-size breakdown we can add HugetlbPages-$size: value kB
> Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
> Acked-by: Joern Engel <joern@xxxxxxxxx>
> Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
Just a small nit-pick, feel free to ignore if this was really intended:
[...]
> +static inline void hugetlb_count_add(long l, struct mm_struct *mm)
> +{
> + atomic_long_add(l, &mm->hugetlb_usage);
> +}
> +
> +static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
> +{
> + atomic_long_sub(l, &mm->hugetlb_usage);
> +}
I can see why you didn't use dec_mm_counter but the ordering could be
same. Other functions which handle counters follow the same template
(target, counter/count).
--
Michal Hocko
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>