Came here to search for the mention of XTDB (formerly known as Crux). I have never tried Datomic and only trivially played with XTDB, does anyone know if there's a comprehensive comparison of the two?
update: So, I asked chatGPT and this is what I got:
----
ChatGPT> Do you know how Datomic and XTDB differ?
Yes, Datomic and XTDB are both database systems, but they differ in a few ways:
1. Architecture: Datomic follows a client-server architecture, where the client sends requests to the server for data manipulation. On the other hand, XTDB is designed as a distributed database system, where data is automatically partitioned across multiple nodes for high availability and scalability.
2. Query Language: Datomic uses the Datalog query language, which is similar to Prolog, for querying the database. XTDB, on the other hand, provides a modern and expressive query language based on Clojure.
3. Data Model: Datomic stores data in the form of entities, attributes, and values. XTDB uses a document-based data model, where each document is a self-contained unit of data.
4. Distributed Transactions: XTDB supports distributed transactions while Datomic does not. This means that XTDB can guarantee the consistency of data across multiple nodes in a distributed system, while Datomic cannot.
5. Open Source: XTDB is open-source, while Datomic is a commercial product, which requires a license to use.
Overall, both Datomic and XTDB have their own unique features and advantages, and the choice between the two depends on the specific requirements and use case of the application.
----
I dunno, it sounds like XTDB is a clear winner here, no?
I'm tickled you asked ChatGPT but I think it misses the the forest for the trees somewhat.
1. Architecture - XTDB is designed to work with Kafka, but it also works with typical JDBC databases as a datastore. Datomic can use SQL databases, DynamoDB or Cassandra if you want distribution. I personally would think long and hard before I introduced a distributed database to my organisation "because it scales".
Part of the value proposition of Datomic is it easily scales read workloads horizontally and by isolating read and writes into separate processes it improves write performance significantly. The metric usually thrown around is 75% of CPU cycles in a traditional RDBMS are concurrency coordination, which is avoided by the Datomic model. That number is quite old now so I don't know if it's still accurate as of 2023.
2. Query language - both use Datalog and support the Datomic `pull` syntax. XTDB also supports SQL.
3. Datomic's EAVT quadruplets are a compelling feature because they are so generic and can be used/re-used in many contexts. A document database would have to fit your use case pretty directly.
4. Datomic has a single transactor process. Do you need distributed transactions? Does Datomic need distributed transactions? You'd have to find someone from say, Nubank, and ask them for war stories. :-)
5. Datomic is now free-as-in-beer.
In my unqualified opinion XTDB is appropriate to choose in the following situations:
- You need to model "valid time" as part of your domain.
- Do you want a document database and are happy with everything that entails?
- You need access to the source code of your database.
- Do you have existing analysts who know SQL but don't know or can't learn Datalog?
