I've got a few questions about the elevator algorithm.
After looking at ll_rw_blk.c and reading the linux-kernel mail archives
it seems to me that the elevator algorithm is used for all kind of block
devices, including hardware-raid controllers (like IBM ServerRaid and
Compaq SMART2). It also seems to me that you are not using the head
position for block write sequence reordering, but the linear address of
the blocks. Are these two "assumptions" true?
With many modern drives you don't know the disks position; there is
all sorts of cunning gymnastics going on inside the drive, you just
access it by sector number -- legacy CHS access doesn't describe
real-life especially on large disks which may contain many zones
(regions where the number of sectors per cylinder is different from
elsewhere on the platter).
--cw
-
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/
This archive was generated by hypermail 2b29 : Sun Jul 23 2000 - 21:00:10 EST