On 20/02/2024 08:31, Christoph Hellwig wrote:
Thanks for writing a good commit message!
NVMe namespaces may define an atomic boundary, whereby no atomic guarantees
are provided for a write which straddles this per-lba space boundary. The
block layer merging policy is such that no merges may occur in which the
resultant request would straddle such a boundary.
Unlike SCSI, NVMe specifies no granularity or alignment rules.
Well, the boundary really is sort of a granularity and alignment,
isn't it?
NVMe does indeed have the boundary rule, but it is not really the same
as SCSI granularity and alignment.
Anyway, I can word that statement to be clearer.
Thanks,
John
