[PATCH 2/2] nvme: add 'queue_if_no_path' semantics

[Sagi Grimberg]

> Compare that to the 'standard', non-CMIC nvme, where with the same setup 
> MD would detach the nvme on its own:
> 
> # cat /proc/mdstat
> Personalities : [raid10]
> md127 : active (auto-read-only) raid10 nvme2n1[1]
>        4189184 blocks super 1.2 2 near-copies [2/1] [_U]
>        bitmap: 0/1 pages [0KB], 65536KB chunk
> 
> unused devices: <none>
> # nvme list
> Node             SN                   Model       Namespace 
> Usage                      Format           FW Rev
> ---------------- -------------------- 
> ---------------------------------------- --------- 
> -------------------------- ---------------- --------
> /dev/nvme0n1     SLESNVME1            QEMU NVMe Ctrl       1          
> 17.18  GB /  17.18  GB    512   B +  0 B   1.0
> /dev/nvme2n1     SLESNVME3            QEMU NVMe Ctrl       1           
> 4.29  GB /   4.29  GB    512   B +  0 B   1.0
> 
> And yes, this is exactly the same setup, the only difference being the 
> CMIC setting for the NVMe device.

I agree with Christoph that we should do exactly the same for all.

Hannes, My understanding here is that you want the device to go away
after the last path disappeared because it breaks md, why don't you
want to have this also for fabrics?

You mention that in fabrics one can manually disconnect, but why should
the user resort to a manual disconnect?

Is something else broken with this behavior? Maybe I am missing
something here?