Re: [RFC PATCH 0/1] nvme-pci: detect I/O queue depth changes after reset

[guzebing <guzebing1612@gmail.com>]

在 2026/5/27 21:19, Christoph Hellwig 写道:
> On Wed, May 27, 2026 at 03:53:19PM +0800, guzebing wrote:
>> This RFC instead takes the smaller approach of detecting the reset-time
>> CAP.MQES change and making it visible.  If the live I/O queue depth
>> shrinks, reset recovery is failed before recreating I/O queues.  If it
>> grows, the driver warns and continues with the existing queue resources.
> 
> Unlike the other version this at least sounds doable without creating
> a complete mess.  So if we can live with this version that'd make me
> much happier.

Thanks, Christoph.

Yes, that is the direction I would like to take here.

The goal of this RFC is to avoid the live queue-depth resize path for 
now and keep the reset recovery policy explicit: fail reset before 
recreating I/O queues if the CAP.MQES-derived depth shrinks, and warn 
but keep using the existing queue resources if it grows.

I will keep this lightweight approach unless there are objections, and 
will wait a bit for other comments before sending a non-RFC version.

Thanks,
Guzebing