Messages in this thread | | | Date | Sat, 25 Mar 2000 23:13:21 -0300 (BRST) | From | Rik van Riel <> | Subject | Re: Virtual vs. physical swap & shared memory forks (clone) |
| |
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/
| |