Re: [PATCH 1/2] nvmet: defer setting ns->enabled to false in nvmet_ns_disable()

[Nilay Shroff]

On 9/18/26 5:38 PM, Christoph Hellwig wrote:
> On Wed, Sep 16, 2026 at 08:39:59PM +0530, Nilay Shroff wrote:
> > In nvmet_ns_disable(), keep ns->enabled set while existing namespace
> > references are being drained, so namespace configuration remains blocked
> > until all in-flight I/O has completed. Set ns->enabled to false only
> > after the namespace references have been drained and the namespace
> > device has been disabled.
> >
> > Since setting ns->enabled to false is deferred in nvmet_ns_disable(),
> > use the NVMET_NS_ENABLED XArray mark in nvmet_req_find_ns() to
> > determine whether a namespace can accept new I/O.
> >
> > Similarly, use the NVMET_NS_ENABLED XArray mark in nvmet_ns_disable()
> > to prevent concurrent callers from starting namespace disable.
>
> This does look sane, but have you looked at profiles if getting the
> xarray tag might touch a lot more cache lines vs the flag?  It might
> make sense to turn enabled into an atomic bit mask and just have two
> flags in there.

Yes, you were correct. Using the XArray mark in the I/O path touches
significantly more cache lines.

I'll fix this as you suggested by using atomic bit flags and send out
the next revision.

Thanks,
--Nilay