All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH V5] memcg: add memory.numastat api for numa statistics
@ 2011-05-20 22:01 Ying Han
  2011-05-20 23:21 ` Rik van Riel
                   ` (2 more replies)
  0 siblings, 3 replies; 7+ messages in thread
From: Ying Han @ 2011-05-20 22:01 UTC (permalink / raw)
  To: KOSAKI Motohiro, Minchan Kim, Daisuke Nishimura, Balbir Singh,
	Tejun Heo, Pavel Emelyanov, KAMEZAWA Hiroyuki, Andrew Morton,
	Li Zefan, Mel Gorman, Christoph Lameter, Johannes Weiner,
	Rik van Riel, Hugh Dickins, Michal Hocko, Dave Hansen,
	Zhu Yanhai
  Cc: linux-mm

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 usecase 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

This patch is based on mmotm-2011-05-06-16-39

change v5..v4:
1. disable the API non-NUMA kernel.

change v4..v3:
1. add per-node "unevictable" value.
2. change the functions to be static.

change v3..v2:
1. calculate the "total" based on the per-memcg lru size instead of rss+cache.
this makes the "total" value to be consistant w/ the per-node values follows
after.

change v2..v1:
1. add also the file and anon pages on per-node distribution.

Signed-off-by: Ying Han <yinghan@google.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
---
 mm/memcontrol.c |  155 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 155 insertions(+), 0 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e14677c..ced414b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1162,6 +1162,93 @@ 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)
 {
@@ -4048,6 +4135,51 @@ 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)
 {
@@ -4058,6 +4190,7 @@ 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;
@@ -4481,6 +4614,22 @@ 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",
@@ -4544,6 +4693,12 @@ 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
-- 
1.7.3.1

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply related	[flat|nested] 7+ messages in thread
end of thread, other threads:[~2011-05-25 11:36 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2011-05-20 22:01 [PATCH V5] memcg: add memory.numastat api for numa statistics Ying Han
2011-05-20 23:21 ` Rik van Riel
2011-05-23  0:08 ` KAMEZAWA Hiroyuki
2011-05-23 20:53   ` Ying Han
2011-05-24 15:46 ` Balbir Singh
2011-05-24 16:54   ` Ying Han
2011-05-25  3:25     ` Balbir Singh

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.