[axboe-block:for-next] [block] bd4a633b6f: fsmark.files_per_sec -64.5% regression

[Christoph Hellwig]

On Mon, Jun 24, 2024 at 03:45:57PM +0200, Niklas Cassel wrote:
> Seems to be ATA SSD:
> https://download.01.org/0day-ci/archive/20240624/202406241546.6bbd44a7-oliver.sang@intel.com/job.yaml
> 
> ssd_partitions: "/dev/disk/by-id/ata-INTEL_SSDSC2BG012T4_BTHC428201ZX1P2OGN-part1"
> 
> Most likely btrfs does something different depending on the nonrot flag
> being set or not. (And like you are suggesting, most likely the value of
> the nonrot flag is somehow different after commit bd4a633b6f)

Yes, btrfs does.  That's why I'm curious about the before and after,
as I can't see any way how they would be set differently.  Right now
I can only claim with vitual AHCI devices, which claim to be rotational,
though.