But let's take a moment to acknowledge the work of John Dyson.

On 03-Apr-98 John S. Dyson wrote:
 
> FreeBSD does not need to use or create three pages like the old VM code
> did, and hasn't for the last year++.  The source says it all!!!  If you
> have a parent and child, there will normally only be two pages after COW,
> unlike the older (seriously broken) VM code.  Collapse operations happen
> very efficiently on FreeBSD, and that has been preliminarily fixed for the
> last 4yrs, and fully fixed for the last 3yrs.  There was a time that we
> did gratuitious collapse, but that was a result of legacy and not need.
> If collapse operations were an issue at all in the performance picture,
> we would have "fixed" the problem.  Frankly, the use of the VM object
> inheritance scheme vs. other schemes is a matter of opinion.  At the
> end of the day, the difference will be negligible, because that isn't
> where the (performance or bug) problems have been in FreeBSD for years.

I can't speak to the technical specifics here.  I can say, however, that when
FreeBSD 2.1 came out I was using 2.0, and the raw _performance_ improvement was
rather dramatic -- a quantum leap, if you will.  There's no question of that.

Of course, Chuck Cranor is correct:  My concerns have typically been about
memory consumption.  For me, performance becomes an issue when the system goes
into swap.  But there too we should acknowledge that up to now, at least,
FreeBSD has better addressed the issue of how the vm responds in a memory
shortage.


--Jim Howard  <jiho@mail.c-zone.net>


----------------------------------
E-Mail: jiho@mail.c-zone.net
Date: 04-Apr-98
Time: 13:21:22

This message was sent by XFMail
----------------------------------