inetd fd leak?

[Denys Vlasenko]

On Friday 04 September 2009 02:28, Doug Graham wrote:
> Conclusion: vfork is totally weird :-)
> 
> > No, it just requires you to be much more careful.
> > But on the bright side, it's many times fater than fork,
> > and exists on NOMMU too.
> >   
> 
> Now you've got me curious about something different.  Is vfork really 
> that much faster on
> modern systems with MMUs?  Certainly I could see it being faster on a system
> without an MMU, where presumably there's no such thing as copy-on-write, 
> but with

vfork is not just faster on NOMMU. It EXISTS on NOMMU. fork does not.

> an MMU does it really take a noticable amount of time just to copy the 
> page tables for
> reasonable-sized processes?

It is big enough to flush 64k L1 dcache.

--
vda