On Sat, 25 Mar 2000, Richard Gooch wrote:
> Rik van Riel writes:
> > On Sat, 25 Mar 2000, Linda Walsh wrote:
> >
> > > The idea is *predictability*. Guarantees of behavior.
> > > Your user deamon is fine for many cases, but it's execution is
> > > not deterministic.
> >
> > Please back up your assertions with code. If you can implement
> > a non-overcommit option which doesn't put overhead in the normal
> > kernel, I'm sure people will use it.
>
> It would probably be helpful to the audience at large to explain
> just how overheads could increase with non-overcommit.
The exact bookkeeping required when you do allocations
and frees on non-allocated memory (for which only the
address space is accounted) will give a little bit
(probably negligable) of overhead.
The inherent swap space overhead non-overcommit gives
isn't an issue here. People can chose for it and will
do so if they think non-overcommit is going to help
them :)
cheers,
Rik
-- The Internet is not a network of computers. It is a network of people. That is its real strength.Wanna talk about the kernel? irc.openprojects.net / #kernelnewbies http://www.conectiva.com/ http://www.surriel.com/
- 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 : Fri Mar 31 2000 - 21:00:16 EST