Then again embedded databases are a great building block for things like etcd. It also might even make sense to have something like this in process because that would remove quite a few failure modes coming from the client connection and simplify deployment
Currently it's even more basic. The current usable parts are a pagecache following the llama approach, some great testing utility libraries, and an index (that you can use as a kv) that follows the bwtree approach. Later it will have structured access support, but it needs some more db components to get there. It is a construction kit as well as a kv.
Not really, when the embedded database is allowed to run its own threads and network connections embedding something like etcd makes perfect sense. It removes the failure modes of the client connection and simplifies deployment.
This is honestly a use case I'm experimenting with using a mix of CRDTs and OT. Our systems are becoming more and more location agnostic and I don't feel that our current data infrastructure is adequate to serve the workloads we're going to be facing as compute migrates to the edge.
It's modular, and there is a paxos implementation, but it has been built totally in simulation so far and I haven't plugged it into an io layer yet. But this is trivial. That said, sled will always be a bwtree index, and the other modular crates will stand on their own.
I am a total devotee to their approach to building simulable systems, although I seek to push it even farther and integrate lineage driven fault injection from an early stage. I see a lot of cool things in what they have done, technically. Sled is free from day one.
