Understanding the rationale behind dropping of "block devices"

[Aijaz Baig]

I am a relative noob to the storage world in general and FreeBSD in
particular. OF what I have been learning of late, I have become somewhat
familiar with such concepts like disk queuing, IOPs, latencies and the likes
I am also reading the classic 'The design and implementation of the FreeBSD
operating system'. However of what I am reading, FreeBSD has "done away"
with "block devices" altogether

Of what I have been reading in that book and elsewhere it appears that the
"block" devices have been dropped out of the architecture. So what I, with
my (still) very limited knowledge of storage, understand this as there are
no drivers in FreeBSD that would deal with blocks of data.

But when I check the disk nodes under /dev I get this
[CODE]ls -l /dev/*disk0
brw-r----- 1 root operator 14, 0 Jan 2 09:39 /dev/disk0
crw-r----- 1 root operator 14, 0 Jan 2 09:39 /dev/rdisk0[/CODE]

where 'b' means block interface and 'c' means char or raw interface. So how
do I reconcile this with what I read about "block devices being gone"
before. What does 'block' mean here?

Of what I know, the block device would be served through the "page cache"
(a place where file system caches it's data and meta data) where as the raw
device would be served via the "buffer cache" where "disk blocks" are
cached by the OS. Thus a block device would be served via the file system
where as the raw device won't. Is this correct?? If yes, then what does
'block' above signify? Or rephrasing the question, what was there earlier
in FreeBSD before 'block device support' was dropped?

I am sure seasoned storage veterans would have a lot more to add. I would
be highly obliged if some one could please elaborate and add more context
to it.

-- 

Best Regards,
Aijaz Baig