Discovery performance is the biggest issue I see. If I deliberately load the same file on a couple of peers, it can take hours (or forever) to be able to find a peer with that file to pin it. It is clumsy and difficult to explicitly connect to peers (because you can't just try to discover peers at an address, you need to include the node ID as well), and even if you manage to enter the right information, you won't necessarily succeed at connecting to the peer the first time.