OT? Linux disk file system design details

[Paul E Condon <pecondon@mesanetworks.net>]

I'm trying to learn more about how data on disk is organized into
directories and files.  I understand how it is that a directory is
really just another file, but marked in such a way that it is subject
to special handling by the OS. But what about inodes and data blocks
(i.e. sectors)? A file of any substantial length is a collection of
data blocks. Is an inode implemented as a data block that is handled
in a special way, or is it a different kind of object (different
length, or different region on disk platter, or ...) ? 

So far, I haven't been able to find an answer by googling. For a
question like this I will probably be able to phrase the search terms
effectively only after I know the answer ;-) 

Pointers?

TIA

-- 
Paul E Condon           
pecondon@mesanetworks.net