[dm-devel] blkio cgroups controller doesn't work with LVM?

[Chris Friesen]

On 02/25/2016 08:53 AM, Mike Snitzer wrote:
> On Thu, Feb 25 2016 at  2:48am -0500,
> Nikolay Borisov <kernel at kyup.com> wrote:
>> On 02/24/2016 08:12 PM, Chris Friesen wrote:
>>>
>>> Are there known limitations with the blkio cgroup controller when used
>>> with LVM?
>>>
>>> I'm using Ubuntu 15.10 with the 4.2 kernel.  I got the same results with
>>> CentOS 7.
>>>
>>> I set up two groups, /sys/fs/cgroup/blkio/test1 and
>>> /sys/fs/cgroup/blkio/test2.  I set the weight for test1 to 500, and the
>>> weight for test2 to 1000.
>>
>> The weighed mode of blkio works only with CFQ scheduler. And as far as I
>> have seen you cannot set CFQ to be the scheduler of DM devices. In this
>> case you can use the BLK io throttling mechanism. That's what I've
>> encountered in my practice. Though I'd be happy to be proven wrong by
>> someone. I believe the following sentence in the blkio controller states
>> that:
>> "
>> First one is proportional weight time based division of disk policy. It
>> is implemented in CFQ. Hence this policy takes effect only on leaf nodes
>> when CFQ is being used.
>> "
>
> Right, LVM created devices are bio-based DM devices in the kernel.
> bio-based block devices do _not_ have an IO scheduler.  Their underlying
> request-based device does.

In my particular case I did ensure that the underlying /dev/sda scheduler was 
set to CFQ.  I had expected that would be sufficient.

> I'm not well-versed on the top-level cgroup interface and how it maps to
> associated resources that are established in the kernel.  But it could
> be that the configuration of blkio cgroup against a bio-based LVM device
> needs to be passed through to the underlying request-based device
> (e.g. /dev/sda4 in Chris's case)?

In my case the process is placed in a cgroup, which is assigned a relative 
weight.  I didn't specify any of per-device weights.

My suspicion is that the cgroup information for the writing process is being 
lost as the request passes through the DM layer.

This is disappointing, given how long both DM and cgroups have been around.

Chris