Re: IO scheduler based IO Controller V2

[Vivek Goyal <vgoyal@redhat.com>]

On Mon, May 11, 2009 at 08:23:09PM +0900, Ryo Tsuruta wrote:
> Hi Vivek,
> 
> From: Vivek Goyal <vgoyal@redhat.com>
> Subject: Re: IO scheduler based IO Controller V2
> Date: Wed, 6 May 2009 21:25:59 -0400
> 
> > On Thu, May 07, 2009 at 09:18:58AM +0900, Ryo Tsuruta wrote:
> > > Hi Vivek,
> > > 
> > > > Ryo, dm-ioband breaks the notion of classes and priority of CFQ because
> > > > of FIFO dispatch of buffered bios. Apart from that it tries to provide
> > > > fairness in terms of actual IO done and that would mean a seeky workload
> > > > will can use disk for much longer to get equivalent IO done and slow down
> > > > other applications. Implementing IO controller at IO scheduler level gives
> > > > us tigher control. Will it not meet your requirements? If you got specific
> > > > concerns with IO scheduler based contol patches, please highlight these and
> > > > we will see how these can be addressed.
> > > 
> > > I'd like to avoid making complicated existing IO schedulers and other
> > > kernel codes and to give a choice to users whether or not to use it.
> > > I know that you chose an approach that using compile time options to
> > > get the same behavior as old system, but device-mapper drivers can be
> > > added, removed and replaced while system is running.
> > > 
> > 
> > Same is possible with IO scheduler based controller. If you don't want
> > cgroup stuff, don't create those. By default everything will be in root
> > group and you will get the old behavior. 
> > 
> > If you want io controller stuff, just create the cgroup, assign weight
> > and move task there. So what more choices do you want which are missing
> > here?
> 
> What I mean to say is that device-mapper drivers can be completely
> removed from the kernel if not used.
> 
> I know that dm-ioband has some issues which can be addressed by your
> IO controller, but I'm not sure your controller works well. So I would
> like to see some benchmark results of your IO controller.
> 

Fair enough. IO scheduler based IO controller is still work in progress
and we have started to get some basic things right. I think after 3-4
iterations of patches, patches will be stable enough and working enough that
I should be able to give some benchmark numbers also.

Currently I am posting the intermediate snapshot of my tree to lkml to get the
design feedback so that if there are fundamental design issues, we can sort
these out.

Thanks
Vivek