Rob Jansen

First of all, it looks like `--load_scale=1.5` is a good default these days to bring the overall amount of data transferred by relays in line with current day Tor. ---...

Second, it does look like clustering has the desired effect of creating longer tails in the client performance metrics. ---   

Third, it looks like even with using an EXACT ip address match as the clustering criteria, we still overshoot performance a bit. ---   

I think the reason that we still overshoot performance is that we are not configuring our new "super relay" clusters with enough resources. Suppose, for example, that we have a...