LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Ryo Tsuruta <ryov@valinux.co.jp>
To: inakoshi.hiroya@jp.fujitsu.com
Cc: containers@lists.linux-foundation.org, dm-devel@redhat.com,
	xen-devel@lists.xensource.com, linux-kernel@vger.kernel.org,
	virtualization@lists.linux-foundation.org
Subject: Re: [Xen-devel] dm-band: The I/O bandwidth controller: Performance Report
Date: Wed, 30 Jan 2008 12:32:02 +0900 (JST)	[thread overview]
Message-ID: <20080130.123202.189729685.ryov@valinux.co.jp> (raw)
In-Reply-To: <479ECAC9.5070709@jp.fujitsu.com>

Hi,

> you mean that you run 128 processes on each user-device pairs?  Namely,
> I guess that
> 
>   user1: 128 processes on sdb5,
>   user2: 128 processes on sdb5,
>   another: 128 processes on sdb5,
>   user2: 128 processes on sdb6.

"User-device pairs" means "band groups", right?
What I actually did is the followings:

  user1: 128 processes on sdb5,
  user2: 128 processes on sdb5,
  user3: 128 processes on sdb5,
  user4: 128 processes on sdb6.

> The second preliminary studies might be:
> - What if you use a different I/O size on each device (or device-user pair)?
> - What if you use a different number of processes on each device (or
> device-user pair)?

There are other ideas of controlling bandwidth, limiting bytes-per-sec,
latency time or something. I think it is possible to implement it if 
a lot of people really require it. I feel there wouldn't be a single
correct answer for this issue. Posting good ideas how it should work
and submitting patches for it are also welcome.

> And my impression is that it's natural dm-band is in device-mapper,
> separated from I/O scheduler.  Because bandwidth control and I/O
> scheduling are two different things, it may be simpler that they are
> implemented in different layers.

I would like to know how dm-band works on various configurations on
various type of hardware. I'll try running dm-band on with other
configurations. Any reports or impressions of dm-band on your machines
are also welcome.

Thanks,
Ryo Tsuruta

      reply	other threads:[~2008-01-30  3:32 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-01-23 12:53 [PATCH 0/2] dm-band: The I/O bandwidth controller: Overview Ryo Tsuruta
2008-01-23 12:56 ` [PATCH 1/2] dm-band: The I/O bandwidth controller: Source code patch Ryo Tsuruta
2008-01-23 13:33   ` Frans Pop
2008-01-23 15:48     ` Ryo Tsuruta
2008-01-27 15:44     ` Frans Pop
2008-01-23 12:58 ` [PATCH 2/2] dm-band: The I/O bandwidth controller: Document Ryo Tsuruta
2008-01-23 19:57   ` Andi Kleen
2008-01-24 10:32     ` Ryo Tsuruta
2008-01-23 14:32 ` [PATCH 0/2] dm-band: The I/O bandwidth controller: Overview Peter Zijlstra
2008-01-23 17:25   ` Ryo Tsuruta
2008-01-23 14:47 ` [dm-devel] " Alasdair G Kergon
2008-01-23 16:21   ` Hirokazu Takahashi
2008-01-24  3:38     ` YAMAMOTO Takashi
2008-01-24 10:14       ` Hirokazu Takahashi
2008-01-25  6:26         ` YAMAMOTO Takashi
2008-01-25  7:07 ` dm-band: The I/O bandwidth controller: Performance Report Ryo Tsuruta
2008-01-29  6:42   ` [Xen-devel] " INAKOSHI Hiroya
2008-01-30  3:32     ` Ryo Tsuruta [this message]

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=20080130.123202.189729685.ryov@valinux.co.jp \
    --to=ryov@valinux.co.jp \
    --cc=containers@lists.linux-foundation.org \
    --cc=dm-devel@redhat.com \
    --cc=inakoshi.hiroya@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=xen-devel@lists.xensource.com \
    --subject='Re: [Xen-devel] dm-band: The I/O bandwidth controller: Performance Report' \
    /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

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).