memcg: fix reclaimable lru check in memcg

Now, in mem_cgroup_hierarchical_reclaim(), mem_cgroup_local_usage() is
used for checking whether the memcg contains reclaimable pages or not.  If
no pages in it, the routine skips it.

But, mem_cgroup_local_usage() contains Unevictable pages and cannot handle
"noswap" condition correctly.  This doesn't work on a swapless system.

This patch adds test_mem_cgroup_reclaimable() and replaces
mem_cgroup_local_usage().  test_mem_cgroup_reclaimable() see LRU counter
and returns correct answer to the caller.  And this new function has
"noswap" argument and can see only FILE LRU if necessary.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: fix kerneldoc layout]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Ying Han <yinghan@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
KAMEZAWA Hiroyuki 2011-07-08 15:39:42 -07:00 committed by Linus Torvalds
parent 0b43c3aab0
commit 4d0c066d29

View file

@ -577,15 +577,6 @@ static long mem_cgroup_read_stat(struct mem_cgroup *mem,
return val;
}
static long mem_cgroup_local_usage(struct mem_cgroup *mem)
{
long ret;
ret = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS);
ret += mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE);
return ret;
}
static void mem_cgroup_swap_statistics(struct mem_cgroup *mem,
bool charge)
{
@ -1129,7 +1120,6 @@ 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)
{
@ -1141,6 +1131,17 @@ static unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup *memcg,
return ret;
}
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;
}
#if MAX_NUMNODES > 1
static unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg)
{
u64 total = 0;
@ -1152,17 +1153,6 @@ static unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg)
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;
@ -1559,6 +1549,28 @@ mem_cgroup_select_victim(struct mem_cgroup *root_mem)
return ret;
}
/**
* test_mem_cgroup_node_reclaimable
* @mem: the target memcg
* @nid: the node ID to be checked.
* @noswap : specify true here if the user wants flle only information.
*
* This function returns whether the specified memcg contains any
* reclaimable pages on a node. Returns true if there are any reclaimable
* pages in the node.
*/
static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *mem,
int nid, bool noswap)
{
if (mem_cgroup_node_nr_file_lru_pages(mem, nid))
return true;
if (noswap || !total_swap_pages)
return false;
if (mem_cgroup_node_nr_anon_lru_pages(mem, nid))
return true;
return false;
}
#if MAX_NUMNODES > 1
/*
@ -1580,15 +1592,8 @@ static void mem_cgroup_may_update_nodemask(struct mem_cgroup *mem)
for_each_node_mask(nid, node_states[N_HIGH_MEMORY]) {
if (mem_cgroup_get_zonestat_node(mem, nid, LRU_INACTIVE_FILE) ||
mem_cgroup_get_zonestat_node(mem, nid, LRU_ACTIVE_FILE))
continue;
if (total_swap_pages &&
(mem_cgroup_get_zonestat_node(mem, nid, LRU_INACTIVE_ANON) ||
mem_cgroup_get_zonestat_node(mem, nid, LRU_ACTIVE_ANON)))
continue;
node_clear(nid, mem->scan_nodes);
if (!test_mem_cgroup_node_reclaimable(mem, nid, false))
node_clear(nid, mem->scan_nodes);
}
}
@ -1627,11 +1632,51 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *mem)
return node;
}
/*
* Check all nodes whether it contains reclaimable pages or not.
* For quick scan, we make use of scan_nodes. This will allow us to skip
* unused nodes. But scan_nodes is lazily updated and may not cotain
* enough new information. We need to do double check.
*/
bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
{
int nid;
/*
* quick check...making use of scan_node.
* We can skip unused nodes.
*/
if (!nodes_empty(mem->scan_nodes)) {
for (nid = first_node(mem->scan_nodes);
nid < MAX_NUMNODES;
nid = next_node(nid, mem->scan_nodes)) {
if (test_mem_cgroup_node_reclaimable(mem, nid, noswap))
return true;
}
}
/*
* Check rest of nodes.
*/
for_each_node_state(nid, N_HIGH_MEMORY) {
if (node_isset(nid, mem->scan_nodes))
continue;
if (test_mem_cgroup_node_reclaimable(mem, nid, noswap))
return true;
}
return false;
}
#else
int mem_cgroup_select_victim_node(struct mem_cgroup *mem)
{
return 0;
}
bool mem_cgroup_reclaimable(struct mem_cgroup *mem, bool noswap)
{
return test_mem_cgroup_node_reclaimable(mem, 0, noswap);
}
#endif
/*
@ -1702,7 +1747,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
}
}
}
if (!mem_cgroup_local_usage(victim)) {
if (!mem_cgroup_reclaimable(victim, noswap)) {
/* this cgroup's local usage == 0 */
css_put(&victim->css);
continue;