Well I explained my rationale above - writes are sequential on the disk level regardless the database. So PostgreSQL shouldn't have much of an advantage in concurrent simple writes (it could even be slower than SQLite). PostgreSQL should be faster in concurrent complex transactions but the question is how complex and how much faster.
Good point. That's a reasonable place to start investigating from.
Personally, I can't be bothered (to much higher priority stuff to do). But if someone else gets around to testing this specifically, I'd be interested in the answers as well just to "make sure" the common understanding isn't wrong. :)
