On Mon, Sep 14, 2020 at 10:59 PM Muchun Song <songmuchun@xxxxxxxxxxxxx> wrote:
>
> In the cgroup v1, we have a numa_stat interface. This is useful for
> providing visibility into the numa locality information within an
> memcg since the pages are allowed to be allocated from any physical
> node. One of the use cases is evaluating application performance by
> combining this information with the application's CPU allocation.
> But the cgroup v2 does not. So this patch adds the missing information.
>
> Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
> Suggested-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Small nits below.
Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
> ---
> changelog in v4:
> 1. Fix some document problems pointed out by Randy Dunlap.
> 2. Remove memory_numa_stat_format() suggested by Shakeel Butt.
>
> changelog in v3:
> 1. Fix compiler error on powerpc architecture reported by kernel test robot.
> 2. Fix a typo from "anno" to "anon".
>
> changelog in v2:
> 1. Add memory.numa_stat interface in cgroup v2.
>
> Documentation/admin-guide/cgroup-v2.rst | 72 +++++++++++++++++++++
> mm/memcontrol.c | 86 +++++++++++++++++++++++++
> 2 files changed, 158 insertions(+)
>
> diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
> index 6be43781ec7f..bcb7b202e88d 100644
> --- a/Documentation/admin-guide/cgroup-v2.rst
> +++ b/Documentation/admin-guide/cgroup-v2.rst
> @@ -1368,6 +1368,78 @@ PAGE_SIZE multiple when read back.
> collapsing an existing range of pages. This counter is not
> present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
>
> + memory.numa_stat
> + A read-only flat-keyed file which exists on non-root cgroups.
> +
> + This breaks down the cgroup's memory footprint into different
> + types of memory, type-specific details, and other information
> + per node on the state of the memory management system.
> +
> + This is useful for providing visibility into the NUMA locality
> + information within an memcg since the pages are allowed to be
> + allocated from any physical node. One of the use cases is evaluating
use case
> + application performance by combining this information with the
> + application's CPU allocation.
> +
> + All memory amounts are in bytes.
> +
> + The output format of memory.numa_stat is::
> +
> + type N0=<bytes in node 0 pages> N1=<bytes in node 1 pages> ...
I would remove 'pages' here as it can be confusing. Just <bytes on node 0>...
> +
> + The entries are ordered to be human readable, and new entries
> + can show up in the middle. Don't rely on items remaining in a
> + fixed position; use the keys to look up specific values!
> +
> + anon
> + Amount of memory per node used in anonymous mappings such
> + as brk(), sbrk(), and mmap(MAP_ANONYMOUS).
> +
> + file
> + Amount of memory per node used to cache filesystem data,
> + including tmpfs and shared memory.
> +
> + kernel_stack
> + Amount of memory per node allocated to kernel stacks.
> +
> + shmem
> + Amount of cached filesystem data per node that is swap-backed,
> + such as tmpfs, shm segments, shared anonymous mmap()s.
> +
> + file_mapped
> + Amount of cached filesystem data per node mapped with mmap().
> +
> + file_dirty
> + Amount of cached filesystem data per node that was modified but
> + not yet written back to disk.
> +
> + file_writeback
> + Amount of cached filesystem data per node that was modified and
> + is currently being written back to disk.
> +
> + anon_thp
> + Amount of memory per node used in anonymous mappings backed by
> + transparent hugepages.
> +
> + inactive_anon, active_anon, inactive_file, active_file, unevictable
> + Amount of memory, swap-backed and filesystem-backed,
> + per node on the internal memory management lists used
> + by the page reclaim algorithm.
> +
> + As these represent internal list state (e.g. shmem pages are on
> + anon memory management lists), inactive_foo + active_foo may not
> + be equal to the value for the foo counter, since the foo counter
> + is type-based, not list-based.
> +
> + slab_reclaimable
> + Amount of memory per node used for storing in-kernel data
> + structures which might be reclaimed, such as dentries and
> + inodes.
> +
> + slab_unreclaimable
> + Amount of memory per node used for storing in-kernel data
> + structures which cannot be reclaimed on memory pressure.
> +
> memory.swap.current
> A read-only single value file which exists on non-root
> cgroups.
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 75cd1a1e66c8..ff919ef3b57b 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -6425,6 +6425,86 @@ static int memory_stat_show(struct seq_file *m, void *v)
> return 0;
> }
>
> +#ifdef CONFIG_NUMA
> +struct numa_stat {
> + const char *name;
> + unsigned int ratio;
> + enum node_stat_item idx;
> +};
> +
> +static struct numa_stat numa_stats[] = {
> + { "anon", PAGE_SIZE, NR_ANON_MAPPED },
> + { "file", PAGE_SIZE, NR_FILE_PAGES },
> + { "kernel_stack", 1024, NR_KERNEL_STACK_KB },
> + { "shmem", PAGE_SIZE, NR_SHMEM },
> + { "file_mapped", PAGE_SIZE, NR_FILE_MAPPED },
> + { "file_dirty", PAGE_SIZE, NR_FILE_DIRTY },
> + { "file_writeback", PAGE_SIZE, NR_WRITEBACK },
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> + /*
> + * The ratio will be initialized in numa_stats_init(). Because
> + * on some architectures, the macro of HPAGE_PMD_SIZE is not
> + * constant(e.g. powerpc).
> + */
> + { "anon_thp", 0, NR_ANON_THPS },
> +#endif
> + { "inactive_anon", PAGE_SIZE, NR_INACTIVE_ANON },
> + { "active_anon", PAGE_SIZE, NR_ACTIVE_ANON },
> + { "inactive_file", PAGE_SIZE, NR_INACTIVE_FILE },
> + { "active_file", PAGE_SIZE, NR_ACTIVE_FILE },
> + { "unevictable", PAGE_SIZE, NR_UNEVICTABLE },
> + { "slab_reclaimable", 1, NR_SLAB_RECLAIMABLE_B },
> + { "slab_unreclaimable", 1, NR_SLAB_UNRECLAIMABLE_B },
> +};
> +
> +static int __init numa_stats_init(void)
> +{
> + int i;
> +
> + for (i = 0; i < ARRAY_SIZE(numa_stats); i++) {
> +#ifdef CONFIG_TRANSPARENT_HUGEPAGE
> + if (numa_stats[i].idx == NR_ANON_THPS)
> + numa_stats[i].ratio = HPAGE_PMD_SIZE;
> +#endif
> + }
> +
> + return 0;
> +}
> +pure_initcall(numa_stats_init);
> +
> +static unsigned long memcg_node_page_state(struct mem_cgroup *memcg,
> + unsigned int nid,
> + enum node_stat_item idx)
> +{
> + VM_BUG_ON(nid >= nr_node_ids);
> + return lruvec_page_state(mem_cgroup_lruvec(memcg, NODE_DATA(nid)), idx);
> +}
> +
> +static int memory_numa_stat_show(struct seq_file *m, void *v)
> +{
> + int i;
> + struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
> +
> + for (i = 0; i < ARRAY_SIZE(numa_stats); i++) {
> + int nid;
> +
> + seq_printf(m, "%s", numa_stats[i].name);
> + for_each_node_state(nid, N_MEMORY) {
> + u64 size;
> +
> + size = memcg_node_page_state(memcg, nid,
> + numa_stats[i].idx);
> + VM_WARN_ON_ONCE(!numa_stats[i].ratio);
> + size *= numa_stats[i].ratio;
> + seq_printf(m, " N%d=%llu", nid, size);
> + }
> + seq_putc(m, '\n');
> + }
> +
> + return 0;
> +}
> +#endif
> +
> static int memory_oom_group_show(struct seq_file *m, void *v)
> {
> struct mem_cgroup *memcg = mem_cgroup_from_seq(m);
> @@ -6502,6 +6582,12 @@ static struct cftype memory_files[] = {
> .name = "stat",
> .seq_show = memory_stat_show,
> },
> +#ifdef CONFIG_NUMA
> + {
> + .name = "numa_stat",
> + .seq_show = memory_numa_stat_show,
> + },
> +#endif
> {
> .name = "oom.group",
> .flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE,
> --
> 2.20.1
>
