Is there any reason the chunk size has to be a power of two?
We're trying to use md devices to stripe over hardware RAID5 arrays, so to align the I/O correctly, I want to set the chunk size to (n - 1) * stripe_size for the underlying array. Which is impossible to do because mdadm (and the kernel) insist on the chunk size being a power of two.
I haven't tried just removing the kernel checks yet ... is there a reason why md is limited to power of two chunk sizes?
Failing that, does anyone know of anything else I can use to stripe block devices together which doesn't have the power of two limitation? device-mapper/LVM seems to have the same problem...