linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Glauber Costa <glommer@parallels.com>
To: David Rientjes <rientjes@google.com>
Cc: cgroups@vger.kernel.org, linux-mm@kvack.org,
	Andrew Morton <akpm@linux-foundation.org>,
	linux-kernel@vger.kernel.org,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Pekka Enberg <penberg@kernel.org>, Michal Hocko <mhocko@suse.cz>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Christoph Lameter <cl@linux.com>,
	devel@openvz.org, kamezawa.hiroyu@jp.fujitsu.com,
	Tejun Heo <tj@kernel.org>, Suleiman Souhlal <suleiman@google.com>
Subject: Re: [PATCH 02/11] memcg: Reclaim when more than one page needed.
Date: Tue, 26 Jun 2012 13:08:48 +0400	[thread overview]
Message-ID: <4FE97C20.8010500@parallels.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1206260146010.16020@chino.kir.corp.google.com>

On 06/26/2012 12:54 PM, David Rientjes wrote:
> On Tue, 26 Jun 2012, Glauber Costa wrote:
>
>>>> + * retries
>>>> + */
>>>> +#define NR_PAGES_TO_RETRY 2
>>>> +
>>>
>>> Should be 1 << PAGE_ALLOC_COSTLY_ORDER?  Where does this number come from?
>>> The changelog doesn't specify.
>>
>> Hocko complained about that, and I changed. Where the number comes from, is
>> stated in the comments: it is a number small enough to have high changes of
>> had been freed by the previous reclaim, and yet around the number of pages of
>> a kernel allocation.
>>
>
> PAGE_ALLOC_COSTLY_ORDER _is_ the threshold used to determine where reclaim
> and compaction is deemed to be too costly to continuously retry, I'm not
> sure why this is any different?
>
> And this is certainly not "around the number of pages of a kernel
> allocation", that depends very heavily on the slab allocator being used;
> slub very often uses order-2 and order-3 page allocations as the default
> settings (it is capped at, you guessed it, PAGE_ALLOC_COSTLY_ORDER
> internally by default) and can be significantly increased on the command
> line.

I am obviously okay with either.

Maybe Michal can comment on this?

>> Of course there are allocations for nr_pages > 2. But 2 will already service
>> the stack most of the time, and most of the slab caches.
>>
>
> Nope, have you checked the output of /sys/kernel/slab/.../order when
> running slub?  On my workstation 127 out of 316 caches have order-2 or
> higher by default.
>

Well, this is still on the side of my argument, since this is still a 
majority of them being low ordered. The code here does not necessarily 
have to retry - if I understand it correctly - we just retry for very 
small allocations because that is where our likelihood of succeeding is.

--
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2012-06-26  9:11 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-25 14:15 [PATCH 00/11] kmem controller for memcg: stripped down version Glauber Costa
2012-06-25 14:15 ` [PATCH 01/11] memcg: Make it possible to use the stock for more than one page Glauber Costa
2012-06-25 17:44   ` Tejun Heo
2012-06-25 22:29     ` Glauber Costa
2012-06-25 22:33       ` Tejun Heo
2012-06-26  4:01   ` David Rientjes
2012-06-25 14:15 ` [PATCH 02/11] memcg: Reclaim when more than one page needed Glauber Costa
2012-06-25 23:33   ` Suleiman Souhlal
2012-06-26  8:39     ` Glauber Costa
2012-06-27 16:16       ` Suleiman Souhlal
2012-06-26  4:09   ` David Rientjes
2012-06-26  7:12     ` Glauber Costa
2012-06-26  8:54       ` David Rientjes
2012-06-26  9:08         ` Glauber Costa [this message]
2012-06-26  9:17           ` David Rientjes
2012-06-26  9:23             ` Glauber Costa
2012-06-27 10:03     ` Glauber Costa
2012-06-27 19:48       ` David Rientjes
2012-06-27 20:47         ` Glauber Costa
2012-06-25 14:15 ` [PATCH 03/11] memcg: change defines to an enum Glauber Costa
2012-06-26  4:11   ` David Rientjes
2012-06-26  8:28     ` Glauber Costa
2012-06-26  9:01       ` David Rientjes
2012-06-25 14:15 ` [PATCH 04/11] kmem slab accounting basic infrastructure Glauber Costa
2012-06-26  4:22   ` David Rientjes
2012-06-26  7:09     ` Glauber Costa
2012-06-25 14:15 ` [PATCH 05/11] Add a __GFP_KMEMCG flag Glauber Costa
2012-06-26  4:25   ` David Rientjes
2012-06-26  7:08     ` Glauber Costa
2012-06-26  9:03       ` David Rientjes
2012-06-25 14:15 ` [PATCH 06/11] memcg: kmem controller infrastructure Glauber Costa
2012-06-25 18:06   ` Tejun Heo
2012-06-25 22:28     ` Glauber Costa
2012-06-25 23:17   ` Andrew Morton
2012-06-26 14:40     ` Glauber Costa
2012-06-26 15:01     ` Glauber Costa
2012-06-26 18:01       ` Andrew Morton
2012-06-26 18:08         ` Tejun Heo
2012-06-26 18:14         ` Glauber Costa
2012-06-26 19:20           ` Andrew Morton
2012-06-26 15:29     ` Glauber Costa
2012-06-26  9:12   ` David Rientjes
2012-06-26  9:17     ` Glauber Costa
2012-06-27  4:01       ` David Rientjes
2012-06-27  9:33         ` Glauber Costa
2012-06-27 19:46           ` David Rientjes
2012-06-25 14:15 ` [PATCH 07/11] mm: Allocate kernel pages to the right memcg Glauber Costa
2012-06-25 18:07   ` Tejun Heo
2012-06-25 22:27     ` Glauber Costa
2012-06-25 14:15 ` [PATCH 08/11] memcg: disable kmem code when not in use Glauber Costa
2012-06-26  5:51   ` Kamezawa Hiroyuki
2012-06-25 14:15 ` [PATCH 09/11] memcg: propagate kmem limiting information to children Glauber Costa
2012-06-25 18:29   ` Tejun Heo
2012-06-25 22:36     ` Glauber Costa
2012-06-25 22:49       ` Tejun Heo
2012-06-25 23:21       ` Andrew Morton
2012-06-26  5:23         ` David Rientjes
2012-06-25 23:23   ` Andrew Morton
2012-06-26  5:24     ` David Rientjes
2012-06-26  5:31       ` Andrew Morton
2012-06-26  7:23         ` Glauber Costa
2012-06-25 14:15 ` [PATCH 10/11] memcg: allow a memcg with kmem charges to be destructed Glauber Costa
2012-06-25 18:34   ` Tejun Heo
2012-06-25 22:25     ` Glauber Costa
2012-06-26  5:59   ` Kamezawa Hiroyuki
2012-06-26  7:21     ` Glauber Costa
2012-06-25 14:15 ` [PATCH 11/11] protect architectures where THREAD_SIZE >= PAGE_SIZE against fork bombs Glauber Costa
2012-06-25 16:55   ` Frederic Weisbecker
2012-06-25 18:38     ` Tejun Heo
2012-06-25 20:57       ` Frederic Weisbecker
2012-06-26 12:48       ` Glauber Costa
2012-06-26 13:38         ` Frederic Weisbecker
2012-06-26 13:37           ` Glauber Costa
2012-06-26 13:44             ` Frederic Weisbecker
2012-06-26  4:57   ` David Rientjes
2012-06-26  5:35     ` Kamezawa Hiroyuki
2012-06-26  7:23     ` Glauber Costa
2012-06-26  8:45       ` David Rientjes
2012-06-26  8:44         ` Glauber Costa
2012-06-26  9:05           ` David Rientjes
2012-06-25 23:27 ` [PATCH 00/11] kmem controller for memcg: stripped down version Andrew Morton
2012-06-26  7:17   ` Glauber Costa
2012-06-26 21:55     ` Andrew Morton
2012-06-27  1:08       ` David Rientjes
2012-06-27  8:39         ` Glauber Costa
2012-06-27  9:29       ` Fork bomb limitation in memcg WAS: " Glauber Costa
2012-06-27 12:29         ` Frederic Weisbecker
2012-06-27 12:28           ` Glauber Costa
2012-06-27 12:35             ` Frederic Weisbecker
2012-06-27 19:38         ` David Rientjes
2012-06-28  9:01           ` Glauber Costa
2012-06-28 22:25             ` Andrew Morton
2012-07-03 11:38               ` Glauber Costa
2012-07-12 15:40                 ` Frederic Weisbecker
2012-08-07 13:59               ` Glauber Costa
2012-08-08 14:15                 ` Glauber Costa

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=4FE97C20.8010500@parallels.com \
    --to=glommer@parallels.com \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=cl@linux.com \
    --cc=devel@openvz.org \
    --cc=fweisbec@gmail.com \
    --cc=hannes@cmpxchg.org \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.cz \
    --cc=penberg@kernel.org \
    --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