
Nov. 94		:	Work begins.

Dec. 94 v0.01	:	First version, directly changing buffers' device
			in getblk, bread and co. No swap. Added an entry
			in /proc for debugging purpose. (NR)

Jan. 95 v0.10	:	Reworked the whole thing, due to some FS problems
			with buffers on the same virtual device not belonging
			to the same real device. Gave up on buffers device
			change, and now using request device, which is
			obviously better. (NR)

Jan. 15/95 v0.11:	FS is now working fine (using an ext2). Swap added
			but not yet tested. (NR)

Jan. 21/95 v0.12:	Fixed a king-size bug in swap, now working flawlessly.
			Some cosmetic changes to /proc/mdstat. Also cleaned
			up md tools and wrote man page. (NR)

Feb. 14/95 v0.13:	Fixed a bug preventing from using any md_dev other
			than md0 ! Some checking added in the kernel.
			Real devices now look like mounted when added to a
			md_dev (use an inode as a lock, so it works with
			fs_may_mount). Updated md tools (now behaving a bit
			like mount). Man page is more confusing. (R)

Mar. 08/95 v0.14:	Introduced a per md_dev 'personality' that indicate
			the way the device is managed. Two personalities are
			currently implemented : linear, which is the old (and
			rather reliable) one, and striped, which is a new one
			(real devices are no more appended to each other, but
			stacked so we have a chunk on first disk, then
			another on second...). The striped personality should
			show some speed improvement with SCSI disks. Updated
			md tools accordingly. (R)

Mar. 20/95 v0.15:	Cleaned up ll_rw_block.c a bit. Debug informations in
			/proc/mdstat are now optionnal (default is off). Major
			number is now 9 (registered number). (R)

Mar. 27/95 v0.16: 	First attempt to handle errors in a RAID-(1 and up)
			system. Using a hacked version of wait_on_buffer.
			It should work fine, but it's not really nice
			to the kernel layering. I think I'd better
			find another idea for that damned thing. Can
			now choose between linear and stipped mode at
			config time. This should save a few bytes on
			low memory systems. (NR)

Apr. 04/95 v0.17:	Ok, things are now much more modular (created
			linear.c and raid0.c). This should make module
			versions very easy to implement. (NR)

Apr. 06/95 v0.18: 	Since some people around don't like the way I trap
			requests in ll_rw_block.c, rewrote the whole
			stuff as a REAL device driver. Now working
			with minimal support in this file (maybe
			somewhat less efficient, since requests are now
			stuffed back to the physical device driver). (NR)

Apr. 11/95 v0.19:	Arghh ! Fixed a fxcking bug that must have been
			here since v0.14 ! Unfortunately, this changes
			blocks repartition on physical devices. Had to
			re-mkfs my md devices :(. Anyway, it works a lot
			better now. Now using read ahead. Really nice
			with my old 1542. The best would be to have a
			per-md-dev read_ahead value, instead of a
			per-major-number value. Adapted to 1.2.5. (R)

Apr. 15/95 v0.20:	Fixed a stupid bug in linear mode (introduced
			with v0.19, thanks to Jeff Uphoff for reporting
			the bug as well as being my first ALPHA tester).
			Released as 0.19b not to confuse people that are
			downloading the patch. New syntax to mdadd and co,
			but this will have to be rewritten soon. (R)

May  01/95 v0.21:	Now using early requests removal, as used in scsi
			and ide drivers. This saves some requests, and
			improves throughput. Fixed a small bug introduced
			by a change in a kernel patch somewhere around
			1.2.4. Still playing with RAID-1 (giving me
			headaches because of non-atomic writes). It is now
			useable, but is awfully slow when writing, and
			no errors traping yet. (NR)

May  05/95 v0.22:	Added modules support. Only having md.c compiled
			into the kernel is mandatory. Personalities are
			optional and can be loaded at run time. Didn't
			use ksyms.c to register exported symbols, but
			instead declared them in md.c . Hope this will
			work nicely (it does... ;-) (R)
