All of lore.kernel.org
 help / color / mirror / Atom feed
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: Ying Han <yinghan@google.com>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"cgroups@vger.kernel.org" <cgroups@vger.kernel.org>,
	Michal Hocko <mhocko@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>, Tejun Heo <tj@kernel.org>,
	Glauber Costa <glommer@parallels.com>,
	Hugh Dickins <hughd@google.com>,
	Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [PATCH 5/7] memcg: divide force_empty into 2 functions, avoid memory reclaim at rmdir
Date: Wed, 18 Apr 2012 16:14:32 +0900	[thread overview]
Message-ID: <4F8E69D8.4070102@jp.fujitsu.com> (raw)
In-Reply-To: <CALWz4iwYX4r5dJmcKFuc+zj_rjMB76dtpbvArdzySF+dyxMohg@mail.gmail.com>

(2012/04/18 2:29), Ying Han wrote:

> On Thu, Apr 12, 2012 at 4:28 AM, KAMEZAWA Hiroyuki
> <kamezawa.hiroyu@jp.fujitsu.com> wrote:
>> Now, at rmdir, memory cgroup's charge will be moved to
>>  - parent if use_hierarchy=1
>>  - root   if use_hierarchy=0
>>
>> Then, we don't have to have memory reclaim code at destroying memcg.
>>
>> This patch divides force_empty to 2 functions as
>>
>>  - memory_cgroup_recharge() ... try to move all charges to ancestors.
>>  - memory_cgroup_force_empty().. try to reclaim all memory.
>>
>> After this patch, memory.force_empty will _not_ move charges to ancestors
>> but just reclaim all pages. (This meets documenation.)
> 
> Not sure why it matches the documentation:
> "
> memory.force_empty>---->------- # trigger forced move charge to parent
> "

I missed this...

> 
> and
> "
>   # echo 0 > memory.force_empty
> 
>   Almost all pages tracked by this memory cgroup will be unmapped and freed.
>   Some pages cannot be freed because they are locked or in-use. Such pages are
>   moved to parent and this cgroup will be empty. This may return -EBUSY if
>   VM is too busy to free/move all pages immediately.
> "
> 


The 1st feature is "will be unmapped and freed".

I'll update Documentation. Thank you.

-Kame




--
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>

WARNING: multiple messages have this Message-ID (diff)
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
To: Ying Han <yinghan-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: "linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org"
	<linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>,
	"cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
	<cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
	Michal Hocko <mhocko-AlSwsSmVLrQ@public.gmane.org>,
	Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>,
	Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>,
	Glauber Costa <glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org>,
	Hugh Dickins <hughd-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
	Andrew Morton
	<akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>
Subject: Re: [PATCH 5/7] memcg: divide force_empty into 2 functions, avoid memory reclaim at rmdir
Date: Wed, 18 Apr 2012 16:14:32 +0900	[thread overview]
Message-ID: <4F8E69D8.4070102@jp.fujitsu.com> (raw)
In-Reply-To: <CALWz4iwYX4r5dJmcKFuc+zj_rjMB76dtpbvArdzySF+dyxMohg-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>

(2012/04/18 2:29), Ying Han wrote:

> On Thu, Apr 12, 2012 at 4:28 AM, KAMEZAWA Hiroyuki
> <kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org> wrote:
>> Now, at rmdir, memory cgroup's charge will be moved to
>>  - parent if use_hierarchy=1
>>  - root   if use_hierarchy=0
>>
>> Then, we don't have to have memory reclaim code at destroying memcg.
>>
>> This patch divides force_empty to 2 functions as
>>
>>  - memory_cgroup_recharge() ... try to move all charges to ancestors.
>>  - memory_cgroup_force_empty().. try to reclaim all memory.
>>
>> After this patch, memory.force_empty will _not_ move charges to ancestors
>> but just reclaim all pages. (This meets documenation.)
> 
> Not sure why it matches the documentation:
> "
> memory.force_empty>---->------- # trigger forced move charge to parent
> "

I missed this...

> 
> and
> "
>   # echo 0 > memory.force_empty
> 
>   Almost all pages tracked by this memory cgroup will be unmapped and freed.
>   Some pages cannot be freed because they are locked or in-use. Such pages are
>   moved to parent and this cgroup will be empty. This may return -EBUSY if
>   VM is too busy to free/move all pages immediately.
> "
> 


The 1st feature is "will be unmapped and freed".

I'll update Documentation. Thank you.

-Kame




  reply	other threads:[~2012-04-18  7:16 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-04-12 11:17 [PATCH v1 0/7] memcg remove pre_destroy KAMEZAWA Hiroyuki
2012-04-12 11:20 ` [PATCH 1/7] res_counter: add a function res_counter_move_parent() KAMEZAWA Hiroyuki
2012-04-12 11:20   ` KAMEZAWA Hiroyuki
2012-04-12 13:22   ` Glauber Costa
2012-04-12 14:30     ` Frederic Weisbecker
2012-04-13  0:57       ` KAMEZAWA Hiroyuki
2012-04-13  0:57         ` KAMEZAWA Hiroyuki
2012-04-13  1:04         ` Frederic Weisbecker
2012-04-13  1:04           ` Frederic Weisbecker
2012-04-13  1:05           ` KAMEZAWA Hiroyuki
2012-04-16 22:19   ` Tejun Heo
2012-04-16 22:19     ` Tejun Heo
2012-04-18  6:59     ` KAMEZAWA Hiroyuki
2012-04-18  6:59       ` KAMEZAWA Hiroyuki
2012-04-16 22:31   ` Tejun Heo
2012-04-18  7:04     ` KAMEZAWA Hiroyuki
2012-04-18  7:04       ` KAMEZAWA Hiroyuki
2012-04-18 17:03       ` Tejun Heo
2012-04-18 17:03         ` Tejun Heo
2012-04-12 11:21 ` [PATCH 2/7] memcg: move charge to parent only when necessary KAMEZAWA Hiroyuki
2012-04-12 11:21   ` KAMEZAWA Hiroyuki
2012-04-16 22:21   ` Tejun Heo
2012-04-16 22:21     ` Tejun Heo
2012-04-18  7:01     ` KAMEZAWA Hiroyuki
2012-04-18  7:01       ` KAMEZAWA Hiroyuki
2012-04-12 11:22 ` [PATCH 3/7] memcg: move charges to root at rmdir() KAMEZAWA Hiroyuki
2012-04-12 11:22   ` KAMEZAWA Hiroyuki
2012-04-16 22:30   ` Tejun Heo
2012-04-16 22:30     ` Tejun Heo
2012-04-18  7:02     ` KAMEZAWA Hiroyuki
2012-04-12 11:24 ` [PATCH 4/7] memcg: remove 'uncharge' argument from mem_cgroup_move_account() KAMEZAWA Hiroyuki
2012-04-12 11:24   ` KAMEZAWA Hiroyuki
2012-04-12 13:27   ` Glauber Costa
2012-04-13  1:01     ` KAMEZAWA Hiroyuki
2012-04-12 11:28 ` [PATCH 5/7] memcg: divide force_empty into 2 functions, avoid memory reclaim at rmdir KAMEZAWA Hiroyuki
2012-04-12 11:28   ` KAMEZAWA Hiroyuki
2012-04-12 13:33   ` Glauber Costa
2012-04-17 17:29   ` Ying Han
2012-04-18  7:14     ` KAMEZAWA Hiroyuki [this message]
2012-04-18  7:14       ` KAMEZAWA Hiroyuki
2012-04-12 11:30 ` [PATCH 6/7] memcg: remove pre_destroy() KAMEZAWA Hiroyuki
2012-04-12 11:30   ` KAMEZAWA Hiroyuki
2012-04-16 22:38   ` Tejun Heo
2012-04-18  7:12     ` KAMEZAWA Hiroyuki
2012-04-18  7:12       ` KAMEZAWA Hiroyuki
2012-04-17 17:47   ` Ying Han
2012-04-17 17:47     ` Ying Han
2012-04-12 11:31 ` [PATCH 7/7] memcg: remove drain_all_stock_sync KAMEZAWA Hiroyuki
2012-04-12 11:31   ` KAMEZAWA Hiroyuki
2012-04-12 13:35   ` Glauber Costa
2012-04-12 13:35     ` Glauber Costa
2012-04-12 13:20 ` [PATCH v1 0/7] memcg remove pre_destroy Glauber Costa
2012-04-12 13:20   ` Glauber Costa
2012-04-12 16:06 ` Tejun Heo
2012-04-12 16:06   ` Tejun Heo
2012-04-12 18:57   ` Aneesh Kumar K.V
2012-04-12 18:57     ` Aneesh Kumar K.V
2012-04-12 23:59     ` KAMEZAWA Hiroyuki
2012-04-13  8:50       ` Michal Hocko
2012-04-13  8:50         ` Michal Hocko
2012-04-13 22:19         ` Aneesh Kumar K.V
2012-04-13 22:19           ` Aneesh Kumar K.V
2012-04-16 22:41 ` Tejun Heo
2012-04-16 22:41   ` Tejun Heo
2012-04-17 17:35 ` Ying Han
2012-04-18  7:15   ` KAMEZAWA Hiroyuki
2012-04-18  7:15     ` 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=4F8E69D8.4070102@jp.fujitsu.com \
    --to=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=glommer@parallels.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.cz \
    --cc=tj@kernel.org \
    --cc=yinghan@google.com \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.