aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHugh Dickins <hugh@veritas.com>2008-02-07 00:14:12 -0800
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2008-02-07 08:42:20 -0800
commit436c6541b13a73790646eb11429bdc8ee50eec41 (patch)
tree45be274e89e7b8db83a98eb3c07031d066e13b16
parentff7283fa3a66823933991ad55a558a3a01d5ab27 (diff)
memcgroup: fix zone isolation OOM
mem_cgroup_charge_common shows a tendency to OOM without good reason, when a memhog goes well beyond its rss limit but with plenty of swap available. Seen on x86 but not on PowerPC; seen when the next patch omits swapcache from memcgroup, but we presume it can happen without. mem_cgroup_isolate_pages is not quite satisfying reclaim's criteria for OOM avoidance. Already it has to scan beyond the nr_to_scan limit when it finds a !LRU page or an active page when handling inactive or an inactive page when handling active. It needs to do exactly the same when it finds a page from the wrong zone (the x86 tests had two zones, the PowerPC tests had only one). Don't increment scan and then decrement it in these cases, just move the incrementation down. Fix recent off-by-one when checking against nr_to_scan. Cut out "Check if the meta page went away from under us", presumably left over from early debugging: no amount of such checks could save us if this list really were being updated without locking. This change does make the unlimited scan while holding two spinlocks even worse - bad for latency and bad for containment; but that's a separate issue which is better left to be fixed a little later. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Pavel Emelianov <xemul@openvz.org> Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--mm/memcontrol.c17
1 files changed, 4 insertions, 13 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e8493fb2d69..9793873d5a9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -260,24 +260,20 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
spin_lock(&mem_cont->lru_lock);
scan = 0;
list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
- if (scan++ > nr_to_scan)
+ if (scan >= nr_to_scan)
break;
page = pc->page;
VM_BUG_ON(!pc);
- if (unlikely(!PageLRU(page))) {
- scan--;
+ if (unlikely(!PageLRU(page)))
continue;
- }
if (PageActive(page) && !active) {
__mem_cgroup_move_lists(pc, true);
- scan--;
continue;
}
if (!PageActive(page) && active) {
__mem_cgroup_move_lists(pc, false);
- scan--;
continue;
}
@@ -288,13 +284,8 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
if (page_zone(page) != z)
continue;
- /*
- * Check if the meta page went away from under us
- */
- if (!list_empty(&pc->lru))
- list_move(&pc->lru, &pc_list);
- else
- continue;
+ scan++;
+ list_move(&pc->lru, &pc_list);
if (__isolate_lru_page(page, mode) == 0) {
list_move(&page->lru, dst);