On Tue, Feb 21, 2017 at 6:45 AM Eric Blake wrote:
> The NBD protocol would like to advertise the optimal I/O
> size to the client; but it would be a layering violation to
> peek into blk_bs(blk)->bl, when we only have a BB.
>
> This copies the existing blk_get_max_transfer()
The NBD protocol would like to advertise the optimal I/O
size to the client; but it would be a layering violation to
peek into blk_bs(blk)->bl, when we only have a BB.
This copies the existing blk_get_max_transfer() in reading
a value from the top BDS; where that value was picked via