Re: Making start/stop idempotent

On Tue, 2008-08-12 at 16:03 +1000, Mark Nottingham wrote:
> On 12/08/2008, at 3:50 PM, Robert Collins wrote:
>
> > On Tue, 2008-08-12 at 15:30 +1000, Mark Nottingham wrote:
> >> Well, here's a patch for the behaviour I described...
> >
> > A patch for 3.x would be nice;
>
> I'll see what I can do, but undoubtedly I'll be slower than others...
>
> > your patch seems fine on the surface, but
> > adding an option does just seem ugly to me :)
>
> Agreed, but I wasn't sure how important staying compatible with
> current behaviour is for others... IME messing with startup/shutdown
> behaviour should be done cautiously...

caution != make-no-changes:)

Oh, one other thing - a unit test to test this would be really good.

-Rob

-- 
GPG key available at: <http://www.robertcollins.net/keys.txt>.