lkml.org 
[lkml]   [2011]   [Jan]   [31]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[patch 3/3] memcg: never OOM when charging huge pages
Date
Huge page coverage should obviously have less priority than the
continued execution of a process.

Never kill a process when charging it a huge page fails. Instead,
give up after the first failed reclaim attempt and fall back to
regular pages.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
mm/memcontrol.c | 10 ++++++++--
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c28072f..9e5de7c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2343,13 +2343,19 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
gfp_t gfp_mask, enum charge_type ctype)
{
struct mem_cgroup *mem = NULL;
+ int page_size = PAGE_SIZE;
struct page_cgroup *pc;
+ bool oom = true;
int ret;
- int page_size = PAGE_SIZE;

if (PageTransHuge(page)) {
page_size <<= compound_order(page);
VM_BUG_ON(!PageTransHuge(page));
+ /*
+ * Never OOM-kill a process for a huge page. The
+ * fault handler will fall back to regular pages.
+ */
+ oom = false;
}

pc = lookup_page_cgroup(page);
@@ -2358,7 +2364,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
return 0;
prefetchw(pc);

- ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page_size);
+ ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, oom, page_size);
if (ret || !mem)
return ret;

--
1.7.3.5


\
 
 \ /
  Last update: 2011-01-31 15:07    [from the cache]
©2003-2011 Jasper Spaans