It’s the first productionization of leaderless consensus protocols. It merges strict serializable transactions into the consensus layer (in 1RTT on the fast path), and has sharding built-in including cross-shard transactions.
It doesn’t support interactive transactions though, so it’s not a drop-in for SQL systems (but I don’t think they are suitable in modern systems anyway, given the latency cost). And it requires quorum reads, since it can’t use leader leases (for obvious reasons), so reads may end up being too slow for many georeplicated setups. But it’s a neat design.
I quite like the Volcano model, it has a certain elegance to it. :) With vectorization and distribution you can get pretty far with it.
For my next real project, I want to build something based on the Accord consensus protocol from Cassandra: https://cwiki.apache.org/confluence/download/attachments/188...
It’s the first productionization of leaderless consensus protocols. It merges strict serializable transactions into the consensus layer (in 1RTT on the fast path), and has sharding built-in including cross-shard transactions.
It doesn’t support interactive transactions though, so it’s not a drop-in for SQL systems (but I don’t think they are suitable in modern systems anyway, given the latency cost). And it requires quorum reads, since it can’t use leader leases (for obvious reasons), so reads may end up being too slow for many georeplicated setups. But it’s a neat design.