On Thu, Mar 07, 2019 at 08:56:32AM -0800, Greg Thelen wrote:
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -3880,6 +3880,7 @@ struct wb_domain *mem_cgroup_wb_domain(struct
> bdi_writeback *wb)
> * @pheadroom: out parameter for number of allocatable pages according to
> memcg
> * @pdirty: out parameter for number of dirty pages
> * @pwriteback: out parameter for number of pages under writeback
> + * @exact: determines exact counters are required, indicates more work.
> *
> * Determine the numbers of file, headroom, dirty, and writeback pages in
> * @wb's memcg. File, dirty and writeback are self-explanatory. Headroom
> @@ -3890,18 +3891,29 @@ struct wb_domain *mem_cgroup_wb_domain(struct
> bdi_writeback *wb)
> * ancestors. Note that this doesn't consider the actual amount of
> * available memory in the system. The caller should further cap
> * *@pheadroom accordingly.
> + *
> + * Return value is the error precision associated with *@pdirty
> + * and *@pwriteback. When @exact is set this a minimal value.
> */
> -void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
> - unsigned long *pheadroom, unsigned long *pdirty,
> - unsigned long *pwriteback)
> +unsigned long
> +mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
> + unsigned long *pheadroom, unsigned long *pdirty,
> + unsigned long *pwriteback, bool exact)
> {
> struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
> struct mem_cgroup *parent;
> + unsigned long precision;
>
> - *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
> -
> + if (exact) {
> + precision = 0;
> + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);
> + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK);
> + } else {
> + precision = MEMCG_CHARGE_BATCH * num_online_cpus();
> + *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
> + *pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
> + }
> /* this should eventually include NR_UNSTABLE_NFS */
> - *pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
> *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
> (1 << LRU_ACTIVE_FILE));
> *pheadroom = PAGE_COUNTER_MAX;
> @@ -3913,6 +3925,8 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb,
> unsigned long *pfilepages,
> *pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
> memcg = parent;
> }
> +
> + return precision;
Have you considered unconditionally using the exact version here?
It does for_each_online_cpu(), but until very, very recently we did
this per default for all stats, for years. It only became a problem in
conjunction with the for_each_memcg loops when frequently reading
memory stats at the top of a very large hierarchy.
balance_dirty_pages() is called against memcgs that actually own the
inodes/memory and doesn't do the additional recursive tree collection.
It's also not *that* hot of a function, and in the io path...
It would simplify this patch immensely.
