The patch titled
memcg: fix reclaimable lru check in memcg
has been added to the -mm tree. Its filename is
memcg-fix-reclaimable-lru-check-in-memcg.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: memcg: fix reclaimable lru check in memcg
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
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.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxx>
Cc: Ying Han <yinghan@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 83 +++++++++++++++++++++++++++++++++++-----------
1 file changed, 64 insertions(+), 19 deletions(-)
diff -puN mm/memcontrol.c~memcg-fix-reclaimable-lru-check-in-memcg mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-fix-reclaimable-lru-check-in-memcg
+++ a/mm/memcontrol.c
@@ -577,15 +577,6 @@ static long mem_cgroup_read_stat(struct
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)
{
@@ -1559,6 +1550,27 @@ mem_cgroup_select_victim(struct mem_cgro
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_nodema
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
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_recla
}
}
}
- if (!mem_cgroup_local_usage(victim)) {
+ if (!mem_cgroup_reclaimable(victim, noswap)) {
/* this cgroup's local usage == 0 */
css_put(&victim->css);
continue;
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
memcg-fix-reclaimable-lru-check-in-memcg.patch
memcg-fix-reclaimable-lru-check-in-memcg-checkpatch-fixes.patch
memcg-fix-reclaimable-lru-check-in-memcg-fix.patch
memcg-fix-numa-scan-information-update-to-be-triggered-by-memory-event.patch
memcg-fix-numa-scan-information-update-to-be-triggered-by-memory-event-fix.patch
mm-preallocate-page-before-lock_page-at-filemap-cow.patch
mm-preallocate-page-before-lock_page-at-filemap-cow-fix.patch
mm-page_cgroupc-simplify-code-by-using-section_align_up-and-section_align_down-macros.patch
memcg-do-not-expose-uninitialized-mem_cgroup_per_node-to-world.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
