On Tue, Oct 22, 2024 at 06:35:11PM +0300, Sagi Grimberg wrote:
On 22/10/2024 17:53, Keith Busch wrote:It's the attributes of the request queue associated with that
On Thu, Oct 17, 2024 at 02:32:18PM -0700, Abhishek Bapat wrote:Won't it be confusing to find queue/ directory in controller nvmeX sysfs
The request_queue is owned by the block layer, so that seems like an
okay place to export it, but attached to some other device's sysfs
directory instead of a gendisk.
I'm just suggesting this because it doesn't sound like this is an nvme
specific problem.
entry?
controller, so I think a queue/ directory under it makes sense. That's
how it looks for gendisks, so why not for disk-less queues?
Many queue attributes only make sense for gendisks, though, so maybe
need to tweak visibility if we decide to do it like this.