From: Glauber Costa <glommer@parallels.com>
To: Paul Menage <paul@paulmenage.org>
Cc: Greg Thelen <gthelen@google.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
containers@lists.osdl.org, netdev@vger.kernel.org,
xemul@parallels.com, "David S. Miller" <davem@davemloft.net>,
Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com>,
"Eric W. Biederman" <ebiederm@xmission.com>,
Suleiman Souhlal <suleiman@google.com>,
Lennart Poettering <lennart@poettering.net>
Subject: Re: [PATCH] per-cgroup tcp buffer limitation
Date: Tue, 13 Sep 2011 15:11:16 -0300 [thread overview]
Message-ID: <4E6F9CC4.2000601@parallels.com> (raw)
In-Reply-To: <CALdu-PC7ESSUHuF4vfVoRFFfkaBt1V28rGW3-O5pT3WtegAh4g@mail.gmail.com>
On 09/13/2011 03:09 PM, Paul Menage wrote:
> Each set of counters (user, kernel, total) will have its own locks,
> contention and other overheads to keep up to date. If userspace
> doesn't care about one or two of the three, then that's mostly wasted.
>
> Now it might be that the accounting of all three can be done with
> little more overhead than that required to update just a split view or
> just a unified view, in which case there's much less argument against
> simplifying and tracking/charging/limiting all three.
What if they are all updated under the same lock ?
The lock argument is very well valid for accounting vs not accounting
kernel memory. But once it is accounted, which counter we account to, I
think, is less of a problem.
--
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: Glauber Costa <glommer@parallels.com>
To: Paul Menage <paul@paulmenage.org>
Cc: Greg Thelen <gthelen@google.com>, <linux-kernel@vger.kernel.org>,
<linux-mm@kvack.org>, <containers@lists.osdl.org>,
<netdev@vger.kernel.org>, <xemul@parallels.com>,
"David S. Miller" <davem@davemloft.net>,
Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com>,
"Eric W. Biederman" <ebiederm@xmission.com>,
Suleiman Souhlal <suleiman@google.com>,
Lennart Poettering <lennart@poettering.net>
Subject: Re: [PATCH] per-cgroup tcp buffer limitation
Date: Tue, 13 Sep 2011 15:11:16 -0300 [thread overview]
Message-ID: <4E6F9CC4.2000601@parallels.com> (raw)
In-Reply-To: <CALdu-PC7ESSUHuF4vfVoRFFfkaBt1V28rGW3-O5pT3WtegAh4g@mail.gmail.com>
On 09/13/2011 03:09 PM, Paul Menage wrote:
> Each set of counters (user, kernel, total) will have its own locks,
> contention and other overheads to keep up to date. If userspace
> doesn't care about one or two of the three, then that's mostly wasted.
>
> Now it might be that the accounting of all three can be done with
> little more overhead than that required to update just a split view or
> just a unified view, in which case there's much less argument against
> simplifying and tracking/charging/limiting all three.
What if they are all updated under the same lock ?
The lock argument is very well valid for accounting vs not accounting
kernel memory. But once it is accounted, which counter we account to, I
think, is less of a problem.
WARNING: multiple messages have this Message-ID (diff)
From: Glauber Costa <glommer@parallels.com>
To: Paul Menage <paul@paulmenage.org>
Cc: Greg Thelen <gthelen@google.com>, <linux-kernel@vger.kernel.org>,
<linux-mm@kvack.org>, <containers@lists.osdl.org>,
<netdev@vger.kernel.org>, <xemul@parallels.com>,
"David S. Miller" <davem@davemloft.net>,
Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com>,
"Eric W. Biederman" <ebiederm@xmission.com>,
Suleiman Souhlal <suleiman@google.com>,
Lennart Poettering <lennart@poettering.net>
Subject: Re: [PATCH] per-cgroup tcp buffer limitation
Date: Tue, 13 Sep 2011 15:11:16 -0300 [thread overview]
Message-ID: <4E6F9CC4.2000601@parallels.com> (raw)
In-Reply-To: <CALdu-PC7ESSUHuF4vfVoRFFfkaBt1V28rGW3-O5pT3WtegAh4g@mail.gmail.com>
On 09/13/2011 03:09 PM, Paul Menage wrote:
> Each set of counters (user, kernel, total) will have its own locks,
> contention and other overheads to keep up to date. If userspace
> doesn't care about one or two of the three, then that's mostly wasted.
>
> Now it might be that the accounting of all three can be done with
> little more overhead than that required to update just a split view or
> just a unified view, in which case there's much less argument against
> simplifying and tracking/charging/limiting all three.
What if they are all updated under the same lock ?
The lock argument is very well valid for accounting vs not accounting
kernel memory. But once it is accounted, which counter we account to, I
think, is less of a problem.
--
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>
next prev parent reply other threads:[~2011-09-13 18:11 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-09-06 2:35 [PATCH] per-cgroup tcp buffer limitation Glauber Costa
2011-09-06 2:35 ` Glauber Costa
2011-09-06 10:00 ` KAMEZAWA Hiroyuki
2011-09-06 10:00 ` KAMEZAWA Hiroyuki
2011-09-06 15:28 ` Glauber Costa
2011-09-06 15:28 ` Glauber Costa
2011-09-06 15:28 ` Glauber Costa
2011-09-06 22:52 ` Glauber Costa
2011-09-06 22:52 ` Glauber Costa
2011-09-06 22:52 ` Glauber Costa
2011-09-06 16:08 ` Greg Thelen
2011-09-06 16:08 ` Greg Thelen
2011-09-06 16:16 ` Glauber Costa
2011-09-06 16:16 ` Glauber Costa
2011-09-06 16:16 ` Glauber Costa
2011-09-06 22:12 ` Greg Thelen
2011-09-06 22:12 ` Greg Thelen
2011-09-06 22:37 ` Glauber Costa
2011-09-06 22:37 ` Glauber Costa
2011-09-06 22:37 ` Glauber Costa
2011-09-07 21:35 ` Greg Thelen
2011-09-07 21:35 ` Greg Thelen
2011-09-08 4:44 ` Glauber Costa
2011-09-08 4:44 ` Glauber Costa
2011-09-08 4:44 ` Glauber Costa
2011-09-08 21:53 ` Greg Thelen
2011-09-08 21:53 ` Greg Thelen
2011-09-09 4:17 ` Glauber Costa
2011-09-09 4:17 ` Glauber Costa
2011-09-09 4:17 ` Glauber Costa
2011-09-09 23:38 ` Greg Thelen
2011-09-09 23:38 ` Greg Thelen
2011-09-12 16:30 ` Glauber Costa
2011-09-12 16:30 ` Glauber Costa
2011-09-12 16:30 ` Glauber Costa
2011-09-12 5:03 ` Paul Menage
2011-09-12 5:03 ` Paul Menage
2011-09-12 16:57 ` Glauber Costa
2011-09-12 16:57 ` Glauber Costa
2011-09-12 16:57 ` Glauber Costa
2011-09-13 6:56 ` Greg Thelen
2011-09-13 6:56 ` Greg Thelen
2011-09-13 18:09 ` Paul Menage
2011-09-13 18:09 ` Paul Menage
2011-09-13 18:11 ` Glauber Costa [this message]
2011-09-13 18:11 ` Glauber Costa
2011-09-13 18:11 ` Glauber Costa
2011-09-13 18:46 ` Paul Menage
2011-09-13 18:46 ` Paul Menage
2011-09-13 19:08 ` Glauber Costa
2011-09-13 19:08 ` Glauber Costa
2011-09-13 19:08 ` Glauber Costa
2011-09-07 2:38 ` Eric Dumazet
2011-09-07 2:38 ` Eric Dumazet
2011-09-07 2:38 ` Eric Dumazet
2011-09-07 1:08 ` Paul Menage
2011-09-07 1:08 ` Paul Menage
2011-09-07 1:09 ` Glauber Costa
2011-09-07 1:09 ` Glauber Costa
2011-09-07 1:09 ` Glauber Costa
2011-09-07 1:29 ` Paul Menage
2011-09-07 1:29 ` Paul Menage
2011-09-07 1:32 ` Glauber Costa
2011-09-07 1:32 ` Glauber Costa
2011-09-07 1:32 ` Glauber Costa
2011-09-09 0:18 ` Rick Jones
2011-09-09 0:18 ` Rick Jones
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=4E6F9CC4.2000601@parallels.com \
--to=glommer@parallels.com \
--cc=containers@lists.osdl.org \
--cc=davem@davemloft.net \
--cc=ebiederm@xmission.com \
--cc=gthelen@google.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=lennart@poettering.net \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=netdev@vger.kernel.org \
--cc=paul@paulmenage.org \
--cc=suleiman@google.com \
--cc=xemul@parallels.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.