On Wed, 2009-05-27 at 16:41 -0600, Alex Rousskov wrote:
> On 05/10/2009 11:08 PM, Robert Collins wrote:
> > On Mon, 2009-05-11 at 16:12 +1200, Amos Jeffries wrote:
> >>
> >> PS. I took another look at the breakage that made me RFC, and I got
> >> the auth and ACL code mixed up. It's auth that is currently fubar again.
> >> But the principle holds: model is broken and we do need to fix it.
> >
> > I'd be strongly inclined to use a linker script to add references rather
> > than the reg.cc files; this would mean we don't need to change code, and
> > should be able to move to dynamic loading if desired (a bunch of .so
> > files on disk, dlopen to use).
>
> What is a linker script? Do we have the expertise to maintain that?
A linker script is simply a set of instructions to the linker telling it
some specific symbols to always include. Yes, I think we do have such
expertise.
> FWIW, I do not think the Reg.cc approach precludes the use of
> dynamically loadable libraries, especially in the C++ world. For
> example, eCAP modules auto-register themselves when dynamically loaded.
>
> Calling Init() in Reg.cc simply makes sure stuff is initialized before
> use. If we move to dynamic libraries, the library can call the same
> Init() method automagically. We may run into initialization order
> problems, but those are unrelated to Reg.cc approach.
Sure, I'll grant that.
-Rob
This archive was generated by hypermail 2.2.0 : Thu May 28 2009 - 12:00:02 MDT