patch is onto mmotm-06-15.
==
>From e58c243f3a5e5ace225a366b4f9d4dfdb0254e28 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Date: Wed, 15 Jun 2011 11:27:04 +0900
Subject: [PATCH 1/7] Fix mem_cgroup_hierarchical_reclaim() to do stable hierarchy walk.
Now, mem_cgroup_hierarchical_reclaim() walks memory cgroups under a tree
from a saved point (root_mem->last_scanned_child) until it visits
root_mem (a top of hierarchy tree) twice.
This means an unstable walk. Assume a tree consists of 6 nodes as
Root-A-B-C-D-E.
When you start a scan from Root.
Root->A->B-C-D-E->Root ==> end with scanning 6 groups.
When you start a scan from "A"
A->B->C->D->E->Root->A->B->C->D->E->Root ==> end with scanning 11 groups.
This is unstable. This patch fixes to visit stable number of nodes at
every scan...visit all nodes only once. In above case,
A->B->C->D->E->Root ==> end.
By this, the core loop can be much cleaner.
And this patch moves drain_all_stock_async() out of loop. Then,
it will be called once if a memcg hit limits.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
---
mm/memcontrol.c | 85 +++++++++++++++++++++++++++-----------------------------
1 file changed, 42 insertions(+), 43 deletions(-)
Index: mmotm-0615/mm/memcontrol.c
===================================================================
--- mmotm-0615.orig/mm/memcontrol.c
+++ mmotm-0615/mm/memcontrol.c
@@ -1641,8 +1641,8 @@ int mem_cgroup_select_victim_node(struct
*
* root_mem is the original ancestor that we've been reclaim from.
*
- * We give up and return to the caller when we visit root_mem twice.
- * (other groups can be removed while we're walking....)
+ * We give up and return to the caller when we visit enough memcgs.
+ * (Typically, we visit the whole memcg tree)
*
* If shrink==true, for avoiding to free too much, this returns immedieately.
*/
@@ -1660,6 +1660,7 @@ static int mem_cgroup_hierarchical_recla
bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
unsigned long excess;
unsigned long nr_scanned;
+ int visit;
excess = res_counter_soft_limit_excess(&root_mem->res) >> PAGE_SHIFT;
@@ -1667,41 +1668,28 @@ static int mem_cgroup_hierarchical_recla
if (!check_soft && root_mem->memsw_is_minimum)
noswap = true;
- while (1) {
+again:
+ if (!shrink) {
+ visit = 0;
+ for_each_mem_cgroup_tree(victim, root_mem)
+ visit++;
+ } else {
+ /*
+ * At shrinking, we check the usage again in caller side.
+ * so, visit children one by one.
+ */
+ visit = 1;
+ }
+ /*
+ * We are not draining per cpu cached charges during soft limit reclaim
+ * because global reclaim doesn't care about charges. It tries to free
+ * some memory and charges will not give any.
+ */
+ if (!check_soft)
+ drain_all_stock_async(root_mem);
+
+ while (visit--) {
victim = mem_cgroup_select_victim(root_mem);
- if (victim == root_mem) {
- loop++;
- /*
- * We are not draining per cpu cached charges during
- * soft limit reclaim because global reclaim doesn't
- * care about charges. It tries to free some memory and
- * charges will not give any.
- */
- if (!check_soft && loop >= 1)
- drain_all_stock_async(root_mem);
- if (loop >= 2) {
- /*
- * If we have not been able to reclaim
- * anything, it might because there are
- * no reclaimable pages under this hierarchy
- */
- if (!check_soft || !total) {
- css_put(&victim->css);
- break;
- }
- /*
- * We want to do more targeted reclaim.
- * excess >> 2 is not to excessive so as to
- * reclaim too much, nor too less that we keep
- * coming back to reclaim from this cgroup
- */
- if (total >= (excess >> 2) ||
- (loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) {
- css_put(&victim->css);
- break;
- }
- }
- }
if (!mem_cgroup_local_usage(victim)) {
/* this cgroup's local usage == 0 */
css_put(&victim->css);
@@ -1717,13 +1705,7 @@ static int mem_cgroup_hierarchical_recla
ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
noswap, get_swappiness(victim));
css_put(&victim->css);
- /*
- * At shrinking usage, we can't check we should stop here or
- * reclaim more. It's depends on callers. last_scanned_child
- * will work enough for keeping fairness under tree.
- */
- if (shrink)
- return ret;
+
total += ret;
if (check_soft) {
if (!res_counter_soft_limit_excess(&root_mem->res))
@@ -1731,6 +1713,23 @@ static int mem_cgroup_hierarchical_recla
} else if (mem_cgroup_margin(root_mem))
return total;
}
+ /*
+ * Basically, softlimit reclaim does deep scan for targeted reclaim. But
+ * if we have not been able to reclaim anything, it might because
+ * there are no reclaimable pages under this hierarchy. So, we don't
+ * retry if total == 0.
+ */
+ if (check_soft && total) {
+ /*
+ * We want to do more targeted reclaim. excess >> 2 is not to
+ * excessive so as to reclaim too much, nor too less that we
+ * keep coming back to reclaim from this cgroup
+ */
+ if (total < (excess >> 2) &&
+ (loop <= MEM_CGROUP_MAX_RECLAIM_LOOPS))
+ goto again;
+ }
+
return total;
}
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx 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@xxxxxxxxx";> email@xxxxxxxxx </a>