That standard religion I just gave you about "stop© only pays for the good stuff, but in mark&sweep you have to pay for the garbage, as well"? It's not true. We all believed it for decades. But Norman Ramsey at harvard has cleverly shown that you can implement mark&sweep with exactly the same asymptotic costs as stop©. This is good news especially for tight-memory systems with homogenous heap data. Norman's observation is really obvious and simple; hardly an impressive result when you see it. Except, uh, that it eluded everyone else for decades. And not because people didn't care; GC has received a lot of attention from researchers. There's a lesson there.