[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <4F608820.8080006@parallels.com>
Date: Wed, 14 Mar 2012 15:59:28 +0400
From: Glauber Costa <glommer@...allels.com>
To: Suleiman Souhlal <suleiman@...gle.com>
CC: Suleiman Souhlal <ssouhlal@...ebsd.org>, <cgroups@...r.kernel.org>,
<kamezawa.hiroyu@...fujitsu.com>, <penberg@...nel.org>,
<cl@...ux.com>, <yinghan@...gle.com>, <hughd@...gle.com>,
<gthelen@...gle.com>, <peterz@...radead.org>,
<dan.magenheimer@...cle.com>, <hannes@...xchg.org>,
<mgorman@...e.de>, <James.Bottomley@...senpartnership.com>,
<linux-mm@...ck.org>, <devel@...nvz.org>,
<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2 03/13] memcg: Uncharge all kmem when deleting a cgroup.
>>> @@ -3719,6 +3721,8 @@ move_account:
>>> /* This is for making all *used* pages to be on LRU. */
>>> lru_add_drain_all();
>>> drain_all_stock_sync(memcg);
>>> + if (!free_all)
>>> + memcg_kmem_move(memcg);
>>
>> Any reason we're not moving kmem charges when free_all is set as well?
>
> Because the slab moving code expects to be synchronized with
> allocations (and itself). We can't call it when there are still tasks
> in the cgroup.
Ok.
Please add an explanation about that.
Oh boy, reading it all now, I started to believe that "free_all" is a
really poor name =(
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists