You don't need to run your mod_perl code in a non-mod_perl enviroment to profile it.

We have a testing framework that lets us run our handler code via ordinary .t files. This makes it convient for us do isolated functional, unit, and performance tests. The latter are known to not reflect deployed reality, but we have other ways of getting data there. Our immediate need is to get profiling working reliably on our .t files. I have my eye on code coverage, but that's a step farther out.