From: Balbir Singh <balbir@linux.vnet.ibm.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Andrew Morton <akpm@linux-foundation.org>,
hugh@veritas.com, menage@google.com, xemul@openvz.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [RFC][PATCH] Remove cgroup member from struct page
Date: Wed, 03 Sep 2008 13:01:15 +0530 [thread overview]
Message-ID: <48BE3D43.7090903@linux.vnet.ibm.com> (raw)
In-Reply-To: <20080903123306.316beb9d.kamezawa.hiroyu@jp.fujitsu.com>
KAMEZAWA Hiroyuki wrote:
> On Tue, 02 Sep 2008 18:07:18 +0530
> Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
>> I understand your concern and I am not trying to reduce memcg's performance - or
>> add a fancy feature. I am trying to make memcg more friendly for distros. I see
>> your point about the overhead. I just got back my results - I see a 4% overhead
>> with the patches. Let me see if I can rework them for better performance.
>>
> Just an idea, by using atomic_ops page_cgroup patch, you can encode page_cgroup->lock
> to page_cgroup->flags and use bit_spinlock(), I think.
> (my new patch set use bit_spinlock on page_cgroup->flags for avoiding some race.)
>
> This will save extra 4 bytes.
Exactly the next step I was thinking about (since we already use it, in the
current form). Thanks for the suggestion!
--
Balbir
WARNING: multiple messages have this Message-ID (diff)
From: Balbir Singh <balbir@linux.vnet.ibm.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
Andrew Morton <akpm@linux-foundation.org>,
hugh@veritas.com, menage@google.com, xemul@openvz.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [RFC][PATCH] Remove cgroup member from struct page
Date: Wed, 03 Sep 2008 13:01:15 +0530 [thread overview]
Message-ID: <48BE3D43.7090903@linux.vnet.ibm.com> (raw)
In-Reply-To: <20080903123306.316beb9d.kamezawa.hiroyu@jp.fujitsu.com>
KAMEZAWA Hiroyuki wrote:
> On Tue, 02 Sep 2008 18:07:18 +0530
> Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
>> I understand your concern and I am not trying to reduce memcg's performance - or
>> add a fancy feature. I am trying to make memcg more friendly for distros. I see
>> your point about the overhead. I just got back my results - I see a 4% overhead
>> with the patches. Let me see if I can rework them for better performance.
>>
> Just an idea, by using atomic_ops page_cgroup patch, you can encode page_cgroup->lock
> to page_cgroup->flags and use bit_spinlock(), I think.
> (my new patch set use bit_spinlock on page_cgroup->flags for avoiding some race.)
>
> This will save extra 4 bytes.
Exactly the next step I was thinking about (since we already use it, in the
current form). Thanks for the suggestion!
--
Balbir
--
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>
next prev parent reply other threads:[~2008-09-03 7:31 UTC|newest]
Thread overview: 144+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-08-31 17:47 [RFC][PATCH] Remove cgroup member from struct page Balbir Singh
2008-08-31 17:47 ` Balbir Singh
2008-09-01 0:01 ` KAMEZAWA Hiroyuki
2008-09-01 0:01 ` KAMEZAWA Hiroyuki
2008-09-01 3:28 ` Balbir Singh
2008-09-01 3:28 ` Balbir Singh
2008-09-01 4:03 ` KAMEZAWA Hiroyuki
2008-09-01 4:03 ` KAMEZAWA Hiroyuki
2008-09-01 5:17 ` KAMEZAWA Hiroyuki
2008-09-01 5:17 ` KAMEZAWA Hiroyuki
2008-09-01 6:16 ` Balbir Singh
2008-09-01 6:16 ` Balbir Singh
2008-09-01 6:09 ` Balbir Singh
2008-09-01 6:09 ` Balbir Singh
2008-09-01 6:24 ` KAMEZAWA Hiroyuki
2008-09-01 6:24 ` KAMEZAWA Hiroyuki
2008-09-01 6:25 ` Balbir Singh
2008-09-01 6:25 ` Balbir Singh
2008-09-01 6:59 ` KAMEZAWA Hiroyuki
2008-09-01 6:59 ` KAMEZAWA Hiroyuki
2008-09-01 6:56 ` Nick Piggin
2008-09-01 6:56 ` Nick Piggin
2008-09-01 7:17 ` Balbir Singh
2008-09-01 7:17 ` Balbir Singh
2008-09-01 7:19 ` KAMEZAWA Hiroyuki
2008-09-01 7:19 ` KAMEZAWA Hiroyuki
2008-09-01 7:43 ` Nick Piggin
2008-09-01 7:43 ` Nick Piggin
2008-09-02 9:24 ` Balbir Singh
2008-09-02 9:24 ` Balbir Singh
2008-09-02 10:02 ` KAMEZAWA Hiroyuki
2008-09-02 10:02 ` KAMEZAWA Hiroyuki
2008-09-02 9:58 ` Balbir Singh
2008-09-02 9:58 ` Balbir Singh
2008-09-02 10:07 ` KAMEZAWA Hiroyuki
2008-09-02 10:07 ` KAMEZAWA Hiroyuki
2008-09-02 10:12 ` Balbir Singh
2008-09-02 10:12 ` Balbir Singh
2008-09-02 10:57 ` KAMEZAWA Hiroyuki
2008-09-02 10:57 ` KAMEZAWA Hiroyuki
2008-09-02 12:37 ` Balbir Singh
2008-09-02 12:37 ` Balbir Singh
2008-09-03 3:33 ` KAMEZAWA Hiroyuki
2008-09-03 3:33 ` KAMEZAWA Hiroyuki
2008-09-03 7:31 ` Balbir Singh [this message]
2008-09-03 7:31 ` Balbir Singh
2008-09-08 15:28 ` Balbir Singh
2008-09-08 15:28 ` Balbir Singh
2008-09-09 3:57 ` KAMEZAWA Hiroyuki
2008-09-09 3:57 ` KAMEZAWA Hiroyuki
2008-09-09 3:58 ` Nick Piggin
2008-09-09 3:58 ` Nick Piggin
2008-09-09 4:53 ` KAMEZAWA Hiroyuki
2008-09-09 4:53 ` KAMEZAWA Hiroyuki
2008-09-09 5:00 ` Nick Piggin
2008-09-09 5:00 ` Nick Piggin
2008-09-09 5:12 ` KAMEZAWA Hiroyuki
2008-09-09 5:12 ` KAMEZAWA Hiroyuki
2008-09-09 12:24 ` Balbir Singh
2008-09-09 12:24 ` Balbir Singh
2008-09-09 12:28 ` Nick Piggin
2008-09-09 12:28 ` Nick Piggin
2008-09-09 12:30 ` kamezawa.hiroyu
2008-09-09 12:30 ` kamezawa.hiroyu
2008-09-09 12:34 ` Balbir Singh
2008-09-09 12:34 ` Balbir Singh
2008-09-10 1:20 ` [Approach #2] " Balbir Singh
2008-09-10 1:20 ` Balbir Singh
2008-09-10 1:49 ` KAMEZAWA Hiroyuki
2008-09-10 1:49 ` KAMEZAWA Hiroyuki
2008-09-10 2:11 ` Balbir Singh
2008-09-10 2:35 ` KAMEZAWA Hiroyuki
2008-09-10 2:35 ` KAMEZAWA Hiroyuki
2008-09-10 20:44 ` Nick Piggin
2008-09-10 20:44 ` Nick Piggin
2008-09-10 11:03 ` KAMEZAWA Hiroyuki
2008-09-10 11:03 ` KAMEZAWA Hiroyuki
2008-09-10 21:02 ` Nick Piggin
2008-09-10 21:02 ` Nick Piggin
2008-09-10 11:27 ` KAMEZAWA Hiroyuki
2008-09-10 11:27 ` KAMEZAWA Hiroyuki
2008-09-10 14:34 ` Balbir Singh
2008-09-10 14:34 ` Balbir Singh
2008-09-10 22:21 ` Dave Hansen
2008-09-10 22:21 ` Dave Hansen
2008-09-10 22:31 ` David Miller
2008-09-10 22:31 ` David Miller, Dave Hansen
2008-09-10 22:36 ` Balbir Singh
2008-09-10 22:36 ` Balbir Singh
2008-09-10 22:56 ` Dave Hansen
2008-09-10 22:56 ` Dave Hansen
2008-09-11 1:35 ` KAMEZAWA Hiroyuki
2008-09-11 1:35 ` KAMEZAWA Hiroyuki
2008-09-11 1:47 ` Balbir Singh
2008-09-11 1:47 ` Balbir Singh
2008-09-11 1:56 ` KAMEZAWA Hiroyuki
2008-09-11 1:56 ` KAMEZAWA Hiroyuki
2008-09-17 23:28 ` [RFC][PATCH] Remove cgroup member from struct page (v3) Balbir Singh
2008-09-17 23:28 ` Balbir Singh
2008-09-18 1:40 ` Andrew Morton
2008-09-18 1:40 ` Andrew Morton
2008-09-18 3:57 ` Balbir Singh
2008-09-18 3:57 ` Balbir Singh
2008-09-18 5:00 ` KAMEZAWA Hiroyuki
2008-09-18 5:00 ` KAMEZAWA Hiroyuki
2008-09-18 4:26 ` Hirokazu Takahashi
2008-09-18 4:26 ` Hirokazu Takahashi
2008-09-18 4:50 ` KAMEZAWA Hiroyuki
2008-09-18 4:50 ` KAMEZAWA Hiroyuki
2008-09-18 6:13 ` Hirokazu Takahashi
2008-09-18 6:13 ` Hirokazu Takahashi
2008-09-18 4:43 ` KAMEZAWA Hiroyuki
2008-09-18 4:43 ` KAMEZAWA Hiroyuki
2008-09-18 4:58 ` Balbir Singh
2008-09-18 4:58 ` Balbir Singh
2008-09-18 5:15 ` KAMEZAWA Hiroyuki
2008-09-18 5:15 ` KAMEZAWA Hiroyuki
2008-09-18 11:01 ` KAMEZAWA Hiroyuki
2008-09-18 11:01 ` KAMEZAWA Hiroyuki
2008-09-18 23:56 ` Balbir Singh
2008-09-18 23:56 ` Balbir Singh
2008-09-19 0:37 ` KAMEZAWA Hiroyuki
2008-09-10 22:38 ` [Approach #2] [RFC][PATCH] Remove cgroup member from struct page Nick Piggin
2008-09-10 22:38 ` Nick Piggin
2008-09-09 4:18 ` Balbir Singh
2008-09-09 4:18 ` Balbir Singh
2008-09-09 4:55 ` KAMEZAWA Hiroyuki
2008-09-09 4:55 ` KAMEZAWA Hiroyuki
2008-09-09 7:37 ` KAMEZAWA Hiroyuki
2008-09-09 7:37 ` KAMEZAWA Hiroyuki
2008-09-01 2:39 ` KAMEZAWA Hiroyuki
2008-09-01 2:39 ` KAMEZAWA Hiroyuki
2008-09-01 3:42 ` Balbir Singh
2008-09-01 3:42 ` Balbir Singh
2008-09-01 9:03 ` Pavel Emelyanov
2008-09-01 9:03 ` Pavel Emelyanov
2008-09-01 9:17 ` Balbir Singh
2008-09-01 9:17 ` Balbir Singh
2008-09-01 9:43 ` Pavel Emelyanov
2008-09-01 9:43 ` Pavel Emelyanov
2008-09-01 13:19 ` Peter Zijlstra
2008-09-01 13:19 ` Peter Zijlstra
2008-09-02 7:35 ` Balbir Singh
2008-09-02 7:35 ` Balbir Singh
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=48BE3D43.7090903@linux.vnet.ibm.com \
--to=balbir@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=hugh@veritas.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=menage@google.com \
--cc=nickpiggin@yahoo.com.au \
--cc=xemul@openvz.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 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.