Date:        Wed, 11 Jun 2003 19:34:03 +0200
    From:        Manuel Bouyer <bouyer@antioche.lip6.fr>
    Message-ID:  <20030611173403.GA25365@antioche.lip6.fr>

  | I don't think it's true for *BSD. I didn't run any tests but I can't see
  | why this would make a difference.

It can be a win or a loss, depending upon the usage patterns of the
filesystems concerned.   If you have a big drive, and say 10% of that
is needed for data that is accessed/updated frequently, you're going
to win by having that data on a partition of its own - that way the seek
time to get to all of the data will be relatively small, if there is
one big partition, ffs will spread the data out all over the drive.

On the other hand, if you happen to have two sets of active data, and
they're in separate partitions at opposite ends of the drive, you can
end up forcing a lot of much bigger seeks than you'd need if all the
data was spread evenly throughout the disc.

So, sometimes it wins, sometimes it loses - and for most people, doing
most average workloads, no-one is going to be able to tell the difference
unless they deliberately create an artificial environment to force it.

kre