Hi Eli > Is there a method to guarantee that this mapping won't fail, even for > different processes, that might have large code or constructors running even > before main?
I'm afraid there is none. That's the nature of the beast. The best you can do is map stuff into a different address range using --base-virtaddr flag in the primary process and hope that this time your "large code or constructors running before main" won't tread into that virtual address space. But even that is not a guarantee by any means. Thanks, Anatoly
