Re: elevator algorithm bug in ll_rw_blk.c

Matthias Urlichs (smurf@noris.de)
20 Nov 1998 09:12:55 +0100

Tim Smith <tzs@tzs.net> writes:
> Note: I'm not saying Linux should measure this stuff and use it. I'm
> just pointing out that the information is available, so if someone wants
> to investigate fancy disk sorting algorithms that take advantage of
> intimate knowledge of the disk, they shouldn't be discouraged by the
> fact that modern disks lie about geometry and use variable density and
> things like that.

The German magazine c't has a regular column about new hard disks and their
access speeds. The did note that some disks actually can switch from track
to track faster than from surface to surface, probably because they need to
re-sync to the servo information on each new surface. Since the
manufacturers aren't stupid, they know this too, and thus reordered the
sectors so that the disk first walks down one surface, then up the next, ...

I think that any fancy reordering should already be embedded in the disk
itself, therefore it doesn't make much sense to put the same into the
kernel.

-- 
Matthias Urlichs  |  noris network GmbH   |   smurf@noris.de  |  ICQ: 20193661
The quote was selected randomly. Really.    |      http://www.noris.de/~smurf/

-- 
The problem with political jokes is they get elected.
                -- Henry Cate VII


-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/