Re: C++ && squid 3.0

On Wed, 21 Mar 2001, Jon Kay wrote:

> Actually, I would suggest that C++ migration for the sake of C++
> migration is not worthwhile.

I agree.

> The best approach, IMHO, is to change each module to C++ as each
> module sees serious change -e.g., the person making significant
> algorithmic changes gets to move things to C++. That minimizes
> the negative impact, since it means that people who understand
> each module will do the job on that module.

Hmm... To me, this approach is exactly what ``C++ migration for the
sake of C++ migration'' is! :)

To get the advantages of C++, one has to design for C++. Squid 2.x is
not designed that way so just "moving things to C++" within each
module is probably not worthwhile. Changing the design one module at a
time does not sound like the right approach either because the
"interesting" part is changing how different modules integrate and
[re]use each other (i.e., "the big picture"). Just rewriting the
interfaces in C++ is trivial (due to current Squid design) and, again,
probably not worthwhile.

These are just my very subjective opinions though. Since I doubt I
will be able to contribute code directly in the foreseeable future, I
will shut up.

Alex.
Received on Wed Mar 21 2001 - 17:40:01 MST