linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vivek Goyal <vgoyal@redhat.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Justin TerAvest <teravest@google.com>,
	m-ikeda@ds.jp.nec.com, jaxboe@fusionio.com,
	linux-kernel@vger.kernel.org, ryov@valinux.co.jp,
	taka@valinux.co.jp, righi.andrea@gmail.com,
	guijianfeng@cn.fujitsu.com, balbir@linux.vnet.ibm.com,
	ctalbott@google.com, nauman@google.com, mrubin@google.com
Subject: Re: [RFC] [PATCH 0/6] Provide cgroup isolation for buffered writes.
Date: Wed, 9 Mar 2011 10:19:40 -0500	[thread overview]
Message-ID: <20110309151940.GC10346@redhat.com> (raw)
In-Reply-To: <20110309142237.6ab82523.kamezawa.hiroyu@jp.fujitsu.com>

On Wed, Mar 09, 2011 at 02:22:37PM +0900, KAMEZAWA Hiroyuki wrote:
[..]

> B) I wonder why the information cannot be recorded in page->private.
>    When page has buffers, you can record the information to buffer struct.
>    About swapio (if you take care of), you can record information to bio.
> 

This sounds very interesting. I am not a vm guy hence I have no idea in
what situations page->private is used and is it ok, to introduce one
more user of it. But if it works, then getting rid of this dependency
on page_cgroup is a huge plug, IMHO.

> Anyway, thank you for the work. And please join the discussion and explain
> "Without it, we didn't see much isolation improvement." with real data.

Agreed. AFAICS, this piece is not going to help much until and unless
we have upper layers fixed (per cgroup dirty ratio and cgroup aware writeout).
So once those two are fixed and in kernel, it will pave the way for
this piece to go in.

Thanks
Vivek

  reply	other threads:[~2011-03-09 15:19 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-03-08 21:20 [RFC] [PATCH 0/6] Provide cgroup isolation for buffered writes Justin TerAvest
2011-03-08 21:20 ` [PATCH 1/6] Add IO cgroup tracking " Justin TerAvest
2011-03-08 21:20 ` [PATCH 2/6] Make async queues per cgroup Justin TerAvest
2011-03-08 21:20 ` [PATCH 3/6] Modify CFQ to use IO tracking information Justin TerAvest
2011-03-08 21:20 ` [PATCH 4/6] With per-cgroup async, don't special case queues Justin TerAvest
2011-03-08 21:20 ` [PATCH 5/6] Add stat for per cgroup writeout done by flusher Justin TerAvest
2011-03-08 21:20 ` [PATCH 6/6] Per cgroup request descriptor counts Justin TerAvest
2011-03-08 22:43 ` [RFC] [PATCH 0/6] Provide cgroup isolation for buffered writes Vivek Goyal
2011-03-08 22:50   ` Vivek Goyal
2011-03-09 18:04     ` Justin TerAvest
2011-03-11  2:47       ` Vivek Goyal
2011-03-11 16:07         ` Justin TerAvest
2011-03-11 16:39           ` Vivek Goyal
2011-03-15 16:41             ` Justin TerAvest
2011-03-15 18:31               ` Vivek Goyal
2011-03-09  5:22 ` KAMEZAWA Hiroyuki
2011-03-09 15:19   ` Vivek Goyal [this message]
2011-03-09 18:05   ` Justin TerAvest
2011-03-10 18:08   ` Justin TerAvest
2011-03-10 18:15     ` Vivek Goyal
2011-03-10 18:57       ` Justin TerAvest
2011-03-10 19:11         ` [RFC] Storing cgroup id in page->private (Was: Re: [RFC] [PATCH 0/6] Provide cgroup isolation for buffered writes.) Vivek Goyal
2011-03-10 19:41           ` Vivek Goyal
2011-03-10 21:15             ` Chris Mason
2011-03-10 21:24               ` Andreas Dilger
2011-03-10 21:38                 ` Vivek Goyal
2011-03-10 21:43                   ` Chris Mason
2011-03-11  1:20                     ` KAMEZAWA Hiroyuki
2011-03-11  1:46                     ` Dave Chinner
2011-03-11  2:15                       ` Vivek Goyal
2011-03-11  2:52                         ` KAMEZAWA Hiroyuki
2011-03-11  3:15                           ` Vivek Goyal
2011-03-11  3:13                             ` 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=20110309151940.GC10346@redhat.com \
    --to=vgoyal@redhat.com \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=ctalbott@google.com \
    --cc=guijianfeng@cn.fujitsu.com \
    --cc=jaxboe@fusionio.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=m-ikeda@ds.jp.nec.com \
    --cc=mrubin@google.com \
    --cc=nauman@google.com \
    --cc=righi.andrea@gmail.com \
    --cc=ryov@valinux.co.jp \
    --cc=taka@valinux.co.jp \
    --cc=teravest@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).