On Mon, 16 Apr 2012 13:46:46 +0800 "kedacomkernel" [off-list ref]
wrote:

This is the man md about:
		When 'near' replicas are chosen, the multiple copies of a given chunk are laid out consecutively  across
       the  stripes  of  the  array,  so the two copies of a datablock will likely be at the same offset on two
       adjacent devices.

"likely" is different from "certainly".  In most cases they are the same
offset.  In some cases they are different offsets.  I think "likely"
describes that well enough.

I think the word "similar" is the same. 

"similar" is not the same as "same", though it is similar .....

"same" means there is no difference.
"similar" means there might be a difference, but it is not a big difference.

Does that clear it up?

NeilBrown