[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <50DCF00B.5040100@jp.fujitsu.com>
Date: Fri, 28 Dec 2012 10:04:11 +0900
From: Kamezawa Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: Sha Zhengju <handai.szj@...il.com>
CC: linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
linux-mm@...ck.org, mhocko@...e.cz, akpm@...ux-foundation.org,
gthelen@...gle.com, fengguang.wu@...el.com, glommer@...allels.com,
Sha Zhengju <handai.szj@...bao.com>
Subject: Re: [PATCH V3 6/8] memcg: Don't account root_mem_cgroup page statistics
(2012/12/26 2:27), Sha Zhengju wrote:
> From: Sha Zhengju <handai.szj@...bao.com>
>
> If memcg is enabled and no non-root memcg exists, all allocated pages
> belongs to root_mem_cgroup and go through root memcg statistics routines
> which brings some overheads. So for the sake of performance, we can give
> up accounting stats of root memcg for MEM_CGROUP_STAT_FILE_MAPPED/FILE_DIRTY
> /WRITEBACK and instead we pay special attention while showing root
> memcg numbers in memcg_stat_show(): as we don't account root memcg stats
> anymore, the root_mem_cgroup->stat numbers are actually 0. But because of
> hierachy, figures of root_mem_cgroup may just represent numbers of pages
> used by its own tasks(not belonging to any other child cgroup). So here we
> fake these root numbers by using stats of global state and all other memcg.
> That is for root memcg:
> nr(MEM_CGROUP_STAT_FILE_MAPPED) = global_page_state(NR_FILE_MAPPED) -
> sum_of_all_memcg(MEM_CGROUP_STAT_FILE_MAPPED);
> Dirty/Writeback pages accounting are in the similar way.
>
> Signed-off-by: Sha Zhengju <handai.szj@...bao.com>
isn't it better to use mem_cgroup_is_root() call rather than
direct comparison (memcg == root_mem_cgroup) ?
Anyway, Ack to this approach.
Thanks,
-Kame
--
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