linux-kernel - Re: [PATCH 0/2] dm-ioband: I/O bandwidth controller v1.7.0: Introduction

Open Source and information security mailing list archives

Message-ID: <2891419e0810080129sb6b35y11362f4bef71c174@mail.gmail.com>
Date:	Wed, 8 Oct 2008 17:29:34 +0900
From:	"Dong-Jae Kang" <baramsori72@...il.com>
To:	"Ryo Tsuruta" <ryov@...inux.co.jp>
Cc:	linux-kernel@...r.kernel.org, dm-devel@...hat.com,
	containers@...ts.linux-foundation.org,
	virtualization@...ts.linux-foundation.org,
	xen-devel@...ts.xensource.com, agk@...rceware.org,
	fernando@....ntt.co.jp, xemul@...nvz.org, balbir@...ux.vnet.ibm.com
Subject: Re: [PATCH 0/2] dm-ioband: I/O bandwidth controller v1.7.0: Introduction

Hi, Ryo Tsuruta

I tested dm-ioband( the latest release, ver 1.7.0 ) IO controller, but
I had a strange result from it.
I have something wrong in test process?
The test process and results are in attached file.
Can you check my testing result and give me a helpful advices and comments?

As you can show in attached file, I tested 4 cases in dm-ioband with
tiobench() IO testing tool like as below
-	1) 3 cgroups with different weight in same ioband device(ioband1) :
Buffered IO
-	2) 3 cgroups with different weight in same ioband device(ioband1) : Direct IO
-	3) 3 cgroups with different weight in each ioband divice(ioband1, 2,
3) : Buffered IO
-	4) 3 cgroups with different weight in each ioband divice(ioband1, 2,
3) : Direct IO
But, IO bandwidth was not nearly controlled by dm-ioband

You can refer the testing tool, tiobench, in
http://sourceforge.net/projects/tiobench/
Originally, tiobench don't support the direct IO mode testing, so I
added the O_DIRECT option to tiobench source code and recompile it to
test the Direct IO cases

Thanks,
Dong-Jae, Kang

---------------------------------------------------------------------
2008/10/3 Ryo Tsuruta <ryov@...inux.co.jp>:
> Hi everyone,
>
> This is the dm-ioband version 1.7.0 release.
>
> Dm-ioband is an I/O bandwidth controller implemented as a device-mapper
> driver, which gives specified bandwidth to each job running on the same
> physical device.
>
> - Can be applied to the kernel 2.6.27-rc5-mm1.
> - Changes from 1.6.0 (posted on Sep 24, 2008):
>  - Fix a problem that processes issuing I/Os are permanently blocked
>    when I/O requests to reclaim pages are consecutively issued.
>
> You can apply the latest bio-cgroup patch to this dm-ioband version.
> The bio-cgroup provides a BIO tracking mechanism with dm-ioband.
> Please see the following site for more information:
>  Block I/O tracking
>  http://people.valinux.co.jp/~ryov/bio-cgroup/
>
> Thanks,
> Ryo Tsuruta
> _______________________________________________
> Containers mailing list
> Containers@...ts.linux-foundation.org
> https://lists.linux-foundation.org/mailman/listinfo/containers
>

Download attachment "dm-ioband_test_result.pdf" of type "application/pdf" (69828 bytes)

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives