Re: [PATCH v3] nvmet: add cgroup_path to charge namespace I/O to a cgroup

[Michal Koutný]

On Wed, Sep 23, 2026 at 08:26:53AM -0700, Peng Yu <yupeng0921@xxxxxxxxx> wrote:
> Scenario:
> * Create multiple nvmet subsystems/namespaces.
> * The namespaces are backed by different LVM logical volumes.
> * Some of the logical volumes share the same physical volumes.

Why are LVMs mentioned? (The test scenario doesn't seem to use those.
And the example is backed by RAM, so where would be any IO to control at
all? Note: I'm only giving this part of my attention span.)

> * The subsystems are exported to different users.
> * We should provide each user a specific iops/bps quota, thus a noisy
>   neighbor won't impact the performance of other logical volumes.

Why cannot you place users into respective cgroups and configure
appropriate per-device limits?

Thanks for providing more context about the scenario so that I can
understand what's the goal and obstacle.

Michal

Attachment: signature.asc
Description: PGP signature