[<prev] [next>] [day] [month] [year] [list]
Message-ID: <87obrz8nlf.fsf@linux.vnet.ibm.com>
Date: Wed, 14 Mar 2012 16:18:44 +0530
From: "Aneesh Kumar K.V" <aneesh.kumar@...ux.vnet.ibm.com>
To: Glauber Costa <glommer@...allels.com>
Cc: linux-mm@...ck.org, mgorman@...e.de,
kamezawa.hiroyu@...fujitsu.com, dhillf@...il.com,
aarcange@...hat.com, mhocko@...e.cz, akpm@...ux-foundation.org,
hannes@...xchg.org, linux-kernel@...r.kernel.org,
cgroups@...r.kernel.org
Subject: Re: [PATCH -V3 4/8] memcg: track resource index in cftype private
On Tue, 13 Mar 2012 17:34:08 +0400, Glauber Costa <glommer@...allels.com> wrote:
> On 03/13/2012 11:07 AM, Aneesh Kumar K.V wrote:
> > if (type == _MEM)
> > ret = mem_cgroup_resize_limit(memcg, val);
> > - else
> > + else if (type == _MEMHUGETLB) {
> > + int idx = MEMFILE_IDX(cft->private);
> > + ret = res_counter_set_limit(&memcg->hugepage[idx], val);
> > + } else
> > ret = mem_cgroup_resize_memsw_limit(memcg, val);
> > break;
> > case RES_SOFT_LIMIT:
>
> What if a user try to set limit < usage ? Isn't there any reclaim that
> we could possibly do, like it is done by normal memcg ?
No, HugeTLB doesn't support reclaim. If we set the limit to a value
below current usage, future allocations will fail, but we don't reclaim.
-aneesh
--
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