[okram]

With Titan/BerkeleyDB you will get blazing performance for a single-machine distribution. One of the wonderful innovations of Titan is vertex-centric indices that is even necessary at single-machine scale.

  http://thinkaurelius.com/2012/10/25/a-solution-to-the-supernode-problem/

Next, if you decide to scale horizontally, then you can simply change the storage.backend=cassandra and thats that (of course, you need to do a bulk data transfer from BerkeleyDB to Cassandra).

[m0nastic]

That's good to know actually; I think that'll probably be a good approach for my application.

For what it's worth, it was seeing a video of you giving a talk about Titan that made me start looking into it. It seems super neat.