From: Glauber Costa <glommer@parallels.com>
To: linux-kernel@vger.kernel.org
Cc: cgroups@vger.kernel.org, linux-mm@kvack.org,
kamezawa.hiroyu@jp.fujitsu.com, Tejun Heo <tj@kernel.org>,
Li Zefan <lizefan@huawei.com>, Greg Thelen <gthelen@google.com>,
Suleiman Souhlal <suleiman@google.com>,
Michal Hocko <mhocko@suse.cz>,
Johannes Weiner <hannes@cmpxchg.org>,
devel@openvz.org, David Rientjes <rientjes@google.com>,
Glauber Costa <glommer@parallels.com>,
Christoph Lameter <cl@linux.com>,
Pekka Enberg <penberg@cs.helsinki.fi>
Subject: [PATCH v3 17/28] skip memcg kmem allocations in specified code regions
Date: Fri, 25 May 2012 17:03:37 +0400 [thread overview]
Message-ID: <1337951028-3427-18-git-send-email-glommer@parallels.com> (raw)
In-Reply-To: <1337951028-3427-1-git-send-email-glommer@parallels.com>
This patch creates a mechanism that skip memcg allocations during
certain pieces of our core code. It basically works in the same way
as preempt_disable()/preempt_enable(): By marking a region under
which all allocations will be accounted to the root memcg.
We need this to prevent races in early cache creation, when we
allocate data using caches that are not necessarily created already.
Signed-off-by: Glauber Costa <glommer@parallels.com>
CC: Christoph Lameter <cl@linux.com>
CC: Pekka Enberg <penberg@cs.helsinki.fi>
CC: Michal Hocko <mhocko@suse.cz>
CC: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
CC: Johannes Weiner <hannes@cmpxchg.org>
CC: Suleiman Souhlal <suleiman@google.com>
---
include/linux/sched.h | 1 +
mm/memcontrol.c | 25 +++++++++++++++++++++++++
2 files changed, 26 insertions(+), 0 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 81a173c..0761dda 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1613,6 +1613,7 @@ struct task_struct {
unsigned long nr_pages; /* uncharged usage */
unsigned long memsw_nr_pages; /* uncharged mem+swap usage */
} memcg_batch;
+ unsigned int memcg_kmem_skip_account;
#endif
#ifdef CONFIG_HAVE_HW_BREAKPOINT
atomic_t ptrace_bp_refcnt;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 44589fb..f3a3812 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -479,6 +479,21 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
EXPORT_SYMBOL(tcp_proto_cgroup);
#endif /* CONFIG_INET */
+static void memcg_stop_kmem_account(void)
+{
+ if (!current->mm)
+ return;
+
+ current->memcg_kmem_skip_account++;
+}
+
+static void memcg_resume_kmem_account(void)
+{
+ if (!current->mm)
+ return;
+
+ current->memcg_kmem_skip_account--;
+}
char *mem_cgroup_cache_name(struct mem_cgroup *memcg, struct kmem_cache *cachep)
{
char *name;
@@ -540,7 +555,9 @@ static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
if (new_cachep)
goto out;
+ memcg_stop_kmem_account();
new_cachep = kmem_cache_dup(memcg, cachep);
+ memcg_resume_kmem_account();
if (new_cachep == NULL) {
new_cachep = cachep;
@@ -631,7 +648,9 @@ static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
if (!css_tryget(&memcg->css))
return;
+ memcg_stop_kmem_account();
cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT);
+ memcg_resume_kmem_account();
if (cw == NULL) {
css_put(&memcg->css);
return;
@@ -666,6 +685,9 @@ struct kmem_cache *__mem_cgroup_get_kmem_cache(struct kmem_cache *cachep,
int idx;
struct task_struct *p;
+ if (!current->mm || current->memcg_kmem_skip_account)
+ return cachep;
+
gfp |= cachep->allocflags;
if (cachep->memcg_params.memcg)
@@ -700,6 +722,9 @@ bool __mem_cgroup_new_kmem_page(struct page *page, gfp_t gfp)
if (!current->mm || in_interrupt())
return true;
+ if (!current->mm || current->memcg_kmem_skip_account)
+ return true;
+
rcu_read_lock();
p = rcu_dereference(current->mm->owner);
memcg = mem_cgroup_from_task(p);
--
1.7.7.6
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. 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@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2012-05-25 13:08 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-05-25 13:03 [PATCH v3 00/28] kmem limitation for memcg Glauber Costa
2012-05-25 13:03 ` [PATCH v3 01/28] slab: move FULL state transition to an initcall Glauber Costa
2012-05-25 13:03 ` [PATCH v3 02/28] memcg: Always free struct memcg through schedule_work() Glauber Costa
2012-05-25 13:03 ` [PATCH v3 03/28] slab: rename gfpflags to allocflags Glauber Costa
2012-05-25 13:03 ` [PATCH v3 04/28] memcg: Make it possible to use the stock for more than one page Glauber Costa
2012-05-25 13:03 ` [PATCH v3 05/28] memcg: Reclaim when more than one page needed Glauber Costa
2012-05-29 14:19 ` Christoph Lameter
2012-05-29 14:20 ` Christoph Lameter
2012-05-29 15:45 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 06/28] slab: use obj_size field of struct kmem_cache when not debugging Glauber Costa
2012-05-25 13:03 ` [PATCH v3 07/28] memcg: change defines to an enum Glauber Costa
2012-05-25 13:03 ` [PATCH v3 08/28] res_counter: don't force return value checking in res_counter_charge_nofail Glauber Costa
2012-05-25 13:03 ` [PATCH v3 09/28] kmem slab accounting basic infrastructure Glauber Costa
2012-05-25 13:03 ` [PATCH v3 10/28] slab/slub: struct memcg_params Glauber Costa
2012-05-25 13:03 ` [PATCH v3 11/28] slub: consider a memcg parameter in kmem_create_cache Glauber Costa
2012-05-25 13:03 ` [PATCH v3 12/28] slab: pass memcg parameter to kmem_cache_create Glauber Costa
2012-05-29 14:27 ` Christoph Lameter
2012-05-29 15:50 ` Glauber Costa
2012-05-29 16:33 ` Christoph Lameter
2012-05-29 16:36 ` Glauber Costa
2012-05-29 16:52 ` Christoph Lameter
2012-05-29 16:59 ` Glauber Costa
2012-05-30 11:01 ` Frederic Weisbecker
2012-05-25 13:03 ` [PATCH v3 13/28] slub: create duplicate cache Glauber Costa
2012-05-29 14:36 ` Christoph Lameter
2012-05-29 15:56 ` Glauber Costa
2012-05-29 16:05 ` Christoph Lameter
2012-05-29 17:05 ` Glauber Costa
2012-05-29 17:25 ` Christoph Lameter
2012-05-29 17:27 ` Glauber Costa
2012-05-29 19:26 ` Christoph Lameter
2012-05-29 19:40 ` Glauber Costa
2012-05-29 19:55 ` Christoph Lameter
2012-05-29 20:08 ` Glauber Costa
2012-05-29 20:21 ` Christoph Lameter
2012-05-29 20:25 ` Glauber Costa
2012-05-30 1:29 ` Tejun Heo
2012-05-30 7:28 ` [Devel] " James Bottomley
2012-05-30 7:54 ` Glauber Costa
2012-05-30 8:02 ` Tejun Heo
2012-05-30 15:37 ` Christoph Lameter
2012-05-29 20:57 ` Suleiman Souhlal
2012-05-25 13:03 ` [PATCH v3 14/28] slab: " Glauber Costa
2012-05-25 13:03 ` [PATCH v3 15/28] slub: always get the cache from its page in kfree Glauber Costa
2012-05-29 14:42 ` Christoph Lameter
2012-05-29 15:59 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 16/28] memcg: kmem controller charge/uncharge infrastructure Glauber Costa
2012-05-29 14:47 ` Christoph Lameter
2012-05-29 16:00 ` Glauber Costa
2012-05-30 12:17 ` Frederic Weisbecker
2012-05-30 12:26 ` Glauber Costa
2012-05-30 12:34 ` Frederic Weisbecker
2012-05-30 12:38 ` Glauber Costa
2012-05-30 13:11 ` Frederic Weisbecker
2012-05-30 13:09 ` Glauber Costa
2012-05-30 13:04 ` Frederic Weisbecker
2012-05-30 13:06 ` Glauber Costa
2012-05-30 13:37 ` Frederic Weisbecker
2012-05-30 13:37 ` Glauber Costa
2012-05-30 13:53 ` Frederic Weisbecker
2012-05-30 13:55 ` Glauber Costa
2012-05-30 15:33 ` Frederic Weisbecker
2012-05-30 16:16 ` Glauber Costa
2012-05-25 13:03 ` Glauber Costa [this message]
2012-05-25 13:03 ` [PATCH v3 18/28] slub: charge allocation to a memcg Glauber Costa
2012-05-29 14:51 ` Christoph Lameter
2012-05-29 16:06 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 19/28] slab: per-memcg accounting of slab caches Glauber Costa
2012-05-29 14:52 ` Christoph Lameter
2012-05-29 16:07 ` Glauber Costa
2012-05-29 16:13 ` Glauber Costa
2012-05-25 13:03 ` [PATCH v3 20/28] memcg: disable kmem code when not in use Glauber Costa
2012-05-25 13:03 ` [PATCH v3 21/28] memcg: destroy memcg caches Glauber Costa
2012-05-25 13:03 ` [PATCH v3 22/28] memcg/slub: shrink dead caches Glauber Costa
2012-05-25 13:03 ` [PATCH v3 23/28] slab: Track all the memcg children of a kmem_cache Glauber Costa
2012-05-25 13:03 ` [PATCH v3 24/28] memcg: Per-memcg memory.kmem.slabinfo file Glauber Costa
2012-05-25 13:03 ` [PATCH v3 25/28] slub: create slabinfo file for memcg Glauber Costa
2012-05-25 13:03 ` [PATCH v3 26/28] slub: track all children of a kmem cache Glauber Costa
2012-05-25 13:03 ` [PATCH v3 27/28] memcg: propagate kmem limiting information to children Glauber Costa
2012-05-25 13:03 ` [PATCH v3 28/28] Documentation: add documentation for slab tracker for memcg Glauber Costa
2012-05-25 13:34 ` [PATCH v3 00/28] kmem limitation " Michal Hocko
2012-05-25 14:34 ` Christoph Lameter
2012-05-28 8:32 ` Glauber Costa
2012-05-29 15:07 ` Christoph Lameter
2012-05-29 15:44 ` Glauber Costa
2012-05-29 16:01 ` Christoph Lameter
2012-06-07 10:26 ` Frederic Weisbecker
2012-06-07 10:53 ` Glauber Costa
2012-06-07 14:00 ` Frederic Weisbecker
2012-06-14 2:24 ` Kamezawa Hiroyuki
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1337951028-3427-18-git-send-email-glommer@parallels.com \
--to=glommer@parallels.com \
--cc=cgroups@vger.kernel.org \
--cc=cl@linux.com \
--cc=devel@openvz.org \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizefan@huawei.com \
--cc=mhocko@suse.cz \
--cc=penberg@cs.helsinki.fi \
--cc=rientjes@google.com \
--cc=suleiman@google.com \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox