RE: elevator algorithm bug in ll_rw_blk.c

Myreen Johan (Johan.Myreen@setec.fi)
Mon, 16 Nov 1998 13:26:59 +0200


>Does anyone else think it might be time for a hard-disk/controller
>which did _not_ do any of this funky optimization?  That way,
>people with smart OS's (like Linux) can have disk drivers
>optimized both for disk geometry and usage, instead of

I'd prefer letting the drive be our friend, and throw requests
at it in any order. Let the drive sort it all out, instead
of trying to beat it at its own game.

After all, only the drive knows what's going on inside
it -- things like how many sectors on which cylinder, which
blocks are automatically remapped to the other edge of
the disk, etc. The 'disk' may even be a flash memory card
with an IDE or SCSI interface.

Of course, we don't live in a perfect world yet, so I guess
it does not hurt to give (IDE) drives a little helping hand
in form of the elevator algorithm.

Johan Myreen
jem@iki.fi

-
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/