On 09/07/2025 02:39, Martin K. Petersen wrote:
The intent for io_min was to convey the physical_block_size in the case
of an individual drive. And for it to be set to the stripe chunk size in
stacking scenarios that would otherwise involve read-modify-write (i.e.
RAID5 and RAID6).
io_opt was meant to communicate the stripe width. Reporting very large
values for io_opt is generally counterproductive since we can't write
multiple gigabytes in a single operation anyway.
logical <= physical <= io_min <= io_opt <= max_sectors <= max_hw_sectors
Does pbs need to be a power-of-2?
The block queue limits and splitting code seems to rely on that, but it
is not policed AFAICS.
The stacking code seems to just want it to be a multiple of lbs, which
itself must be a power-of-2.
Thanks,
John
