On Tue, 3 Mar 2020 18:20:58 -0800 Shakeel Butt <shakeelb@xxxxxxxxxx> wrote:
> Currently reading memory.numa_stat traverses the underlying memcg tree
> multiple times to accumulate the stats to present the hierarchical view
> of the memcg tree. However the kernel already maintains the hierarchical
> view of the stats and use it in memory.stat. Just use the same mechanism
> in memory.numa_stat as well.
>
> I ran a simple benchmark which reads root_mem_cgroup's memory.numa_stat
> file in the presense of 10000 memcgs. The results are:
>
> Without the patch:
> $ time cat /dev/cgroup/memory/memory.numa_stat > /dev/null
>
> real 0m0.700s
> user 0m0.001s
> sys 0m0.697s
>
> With the patch:
> $ time cat /dev/cgroup/memory/memory.numa_stat > /dev/null
>
> real 0m0.001s
> user 0m0.001s
> sys 0m0.000s
>
Can't you do better than that ;)
>
> + page_state = tree ? lruvec_page_state : lruvec_page_state_local;
> ...
>
> + page_state = tree ? memcg_page_state : memcg_page_state_local;
>
All four of these functions are inlined. Taking their address in this
fashion will force the compiler to generate out-of-line copies.
If we do it the uglier-and-maybe-a-bit-slower way:
--- a/mm/memcontrol.c~memcg-optimize-memorynuma_stat-like-memorystat-fix
+++ a/mm/memcontrol.c
@@ -3658,17 +3658,16 @@ static unsigned long mem_cgroup_node_nr_
struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
unsigned long nr = 0;
enum lru_list lru;
- unsigned long (*page_state)(struct lruvec *lruvec,
- enum node_stat_item idx);
VM_BUG_ON((unsigned)nid >= nr_node_ids);
- page_state = tree ? lruvec_page_state : lruvec_page_state_local;
-
for_each_lru(lru) {
if (!(BIT(lru) & lru_mask))
continue;
- nr += page_state(lruvec, NR_LRU_BASE + lru);
+ if (tree)
+ nr += lruvec_page_state(lruvec, NR_LRU_BASE + lru);
+ else
+ nr += lruvec_page_state_local(lruvec, NR_LRU_BASE + lru);
}
return nr;
}
@@ -3679,14 +3678,14 @@ static unsigned long mem_cgroup_nr_lru_p
{
unsigned long nr = 0;
enum lru_list lru;
- unsigned long (*page_state)(struct mem_cgroup *memcg, int idx);
-
- page_state = tree ? memcg_page_state : memcg_page_state_local;
for_each_lru(lru) {
if (!(BIT(lru) & lru_mask))
continue;
- nr += page_state(memcg, NR_LRU_BASE + lru);
+ if (tree)
+ nr += memcg_page_state(memcg, NR_LRU_BASE + lru);
+ else
+ nr += memcg_page_state_local(memcg, NR_LRU_BASE + lru);
}
return nr;
}
Then we get:
text data bss dec hex filename
now: 106705 35641 1024 143370 2300a mm/memcontrol.o
shakeel: 107111 35657 1024 143792 231b0 mm/memcontrol.o
shakeel+the-above: 106805 35657 1024 143486 2307e mm/memcontrol.o
Which do we prefer? The 100-byte patch or the 406-byte patch?
