memcg: add memory.numastat api for numa statistics

The new API exports numa_maps per-memcg basis.  This is a piece of useful
information where it exports per-memcg page distribution across real numa
nodes.

One of the usecases is evaluating application performance by combining
this information w/ the cpu allocation to the application.

The output of the memory.numastat tries to follow w/ simiar format of
numa_maps like:

  total=<total pages> N0=<node 0 pages> N1=<node 1 pages> ...
  file=<total file pages> N0=<node 0 pages> N1=<node 1 pages> ...
  anon=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...
  unevictable=<total anon pages> N0=<node 0 pages> N1=<node 1 pages> ...

And we have per-node:

  total = file + anon + unevictable

  $ cat /dev/cgroup/memory/memory.numa_stat
  total=250020 N0=87620 N1=52367 N2=45298 N3=64735
  file=225232 N0=83402 N1=46160 N2=40522 N3=55148
  anon=21053 N0=3424 N1=6207 N2=4776 N3=6646
  unevictable=3735 N0=794 N1=0 N2=0 N3=2941

Signed-off-by: Ying Han <yinghan@google.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Minchan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cc48a6854f7e5aa9ac9f38507b4637bed7e63114..4021fcd71b60eddc9f50c420c5c4bd748e62b8cd 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1089,6 +1089,93 @@ unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg,
        return MEM_CGROUP_ZSTAT(mz, lru);
 }
 
+#ifdef CONFIG_NUMA
+static unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup *memcg,
+                                                       int nid)
+{
+       unsigned long ret;
+
+       ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_FILE) +
+               mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_FILE);
+
+       return ret;
+}
+
+static unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg)
+{
+       u64 total = 0;
+       int nid;
+
+       for_each_node_state(nid, N_HIGH_MEMORY)
+               total += mem_cgroup_node_nr_file_lru_pages(memcg, nid);
+
+       return total;
+}
+
+static unsigned long mem_cgroup_node_nr_anon_lru_pages(struct mem_cgroup *memcg,
+                                                       int nid)
+{
+       unsigned long ret;
+
+       ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_ANON) +
+               mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_ANON);
+
+       return ret;
+}
+
+static unsigned long mem_cgroup_nr_anon_lru_pages(struct mem_cgroup *memcg)
+{
+       u64 total = 0;
+       int nid;
+
+       for_each_node_state(nid, N_HIGH_MEMORY)
+               total += mem_cgroup_node_nr_anon_lru_pages(memcg, nid);
+
+       return total;
+}
+
+static unsigned long
+mem_cgroup_node_nr_unevictable_lru_pages(struct mem_cgroup *memcg, int nid)
+{
+       return mem_cgroup_get_zonestat_node(memcg, nid, LRU_UNEVICTABLE);
+}
+
+static unsigned long
+mem_cgroup_nr_unevictable_lru_pages(struct mem_cgroup *memcg)
+{
+       u64 total = 0;
+       int nid;
+
+       for_each_node_state(nid, N_HIGH_MEMORY)
+               total += mem_cgroup_node_nr_unevictable_lru_pages(memcg, nid);
+
+       return total;
+}
+
+static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
+                                                       int nid)
+{
+       enum lru_list l;
+       u64 total = 0;
+
+       for_each_lru(l)
+               total += mem_cgroup_get_zonestat_node(memcg, nid, l);
+
+       return total;
+}
+
+static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg)
+{
+       u64 total = 0;
+       int nid;
+
+       for_each_node_state(nid, N_HIGH_MEMORY)
+               total += mem_cgroup_node_nr_lru_pages(memcg, nid);
+
+       return total;
+}
+#endif /* CONFIG_NUMA */
+
 struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
                                                      struct zone *zone)
 {
@@ -3944,6 +4031,51 @@ mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
                mem_cgroup_get_local_stat(iter, s);
 }
 
+#ifdef CONFIG_NUMA
+static int mem_control_numa_stat_show(struct seq_file *m, void *arg)
+{
+       int nid;
+       unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
+       unsigned long node_nr;
+       struct cgroup *cont = m->private;
+       struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
+
+       total_nr = mem_cgroup_nr_lru_pages(mem_cont);
+       seq_printf(m, "total=%lu", total_nr);
+       for_each_node_state(nid, N_HIGH_MEMORY) {
+               node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid);
+               seq_printf(m, " N%d=%lu", nid, node_nr);
+       }
+       seq_putc(m, '\n');
+
+       file_nr = mem_cgroup_nr_file_lru_pages(mem_cont);
+       seq_printf(m, "file=%lu", file_nr);
+       for_each_node_state(nid, N_HIGH_MEMORY) {
+               node_nr = mem_cgroup_node_nr_file_lru_pages(mem_cont, nid);
+               seq_printf(m, " N%d=%lu", nid, node_nr);
+       }
+       seq_putc(m, '\n');
+
+       anon_nr = mem_cgroup_nr_anon_lru_pages(mem_cont);
+       seq_printf(m, "anon=%lu", anon_nr);
+       for_each_node_state(nid, N_HIGH_MEMORY) {
+               node_nr = mem_cgroup_node_nr_anon_lru_pages(mem_cont, nid);
+               seq_printf(m, " N%d=%lu", nid, node_nr);
+       }
+       seq_putc(m, '\n');
+
+       unevictable_nr = mem_cgroup_nr_unevictable_lru_pages(mem_cont);
+       seq_printf(m, "unevictable=%lu", unevictable_nr);
+       for_each_node_state(nid, N_HIGH_MEMORY) {
+               node_nr = mem_cgroup_node_nr_unevictable_lru_pages(mem_cont,
+                                                                       nid);
+               seq_printf(m, " N%d=%lu", nid, node_nr);
+       }
+       seq_putc(m, '\n');
+       return 0;
+}
+#endif /* CONFIG_NUMA */
+
 static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
                                 struct cgroup_map_cb *cb)
 {
@@ -3954,6 +4086,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
        memset(&mystat, 0, sizeof(mystat));
        mem_cgroup_get_local_stat(mem_cont, &mystat);
 
+
        for (i = 0; i < NR_MCS_STAT; i++) {
                if (i == MCS_SWAP && !do_swap_account)
                        continue;
@@ -4377,6 +4510,22 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
        return 0;
 }
 
+#ifdef CONFIG_NUMA
+static const struct file_operations mem_control_numa_stat_file_operations = {
+       .read = seq_read,
+       .llseek = seq_lseek,
+       .release = single_release,
+};
+
+static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
+{
+       struct cgroup *cont = file->f_dentry->d_parent->d_fsdata;
+
+       file->f_op = &mem_control_numa_stat_file_operations;
+       return single_open(file, mem_control_numa_stat_show, cont);
+}
+#endif /* CONFIG_NUMA */
+
 static struct cftype mem_cgroup_files[] = {
        {
                .name = "usage_in_bytes",
@@ -4440,6 +4589,12 @@ static struct cftype mem_cgroup_files[] = {
                .unregister_event = mem_cgroup_oom_unregister_event,
                .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL),
        },
+#ifdef CONFIG_NUMA
+       {
+               .name = "numa_stat",
+               .open = mem_control_numa_stat_open,
+       },
+#endif
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP