Redis Labs announced Redis Database 7.0. The in-memory NoSQL database software will deliver faster performance for a globally distributed Redis database, more reliable data, better searches and AI assistance, the company said at Redisconf yesterday.
Specifically Redis Labs is announcing:-
- RedisRAFT to provide strong consistency
- RediSearch with new indexing and querying capabilities
- RedisJSON in-memory manipulation of JSON documents
- RedisAI inferencing engine
“Through these innovations, we believe Redis has become the de facto data platform for a new wave of digital experiences by changing the way developers can build true real-time applications and then deploy them anywhere, cloud, multi-cloud, hybrid-cloud or on-premises, in a globally distributed manner, closer to where their customers are,” Yiftach Shoolman, Redis Labs co-founder and CTO, said.
RedisRAFT uses the Raft (Reliable, Replicated, Redundant, And Fault-Tolerant) consensus algorithm in which many servers agree on a leader server and values such as a hash table describing cluster state transitions in a fault-tolerant server cluster. The consensus value agreement continues if a minority of the servers fail.
RAFT enables parallel processes in a cluster to see data accesses in the same order. This contrasts with ‘weak consistency’, where cluster nodes can apply data accesses in a different order resulting in data value differences between the servers. These can be corrected in a ‘eventually-consistent’ system but that means wrong data values may occur, such as when a server is unavailable because of a fault.
The benefit of RedisRAFT is that it provides both strong consistency and high-availability. It has passed the Jepsen tests, which check data consistency guarantees with no unresolved issues and with Redis performance levels maintained.
RedisJSON provides a tree-like, hierarchical document store in which storage and querying is faster than using JSON with the Lua programming language and core Redis data structures. RediSearch has gained integration with RedisJSON so that developers can now natively store, index, query, and perform full-text search on documents faster than before. Redis says that the combination of RediSearch and RedisJSON provides integrated data models which can combine data from different sources.
RediSearch and RedisJSON& can be deployed in a globally distributed manner, useful for disaster recovery purposes and also to enable applications to run where the customers are located and so save time by avoiding data movement.
Active:Active and RedisAI
Redis says it uses an active:active geo-distributed topology based on conflict-free replicated data types (CRDTS) in a global database running across multiple clusters. It claims this provides global data distribution, spanning on-premises, multiple public clouds and hybrid environments, with local access speed, to deliver sub-millisecond latency.
The RedisAI inferencing engine provides a feature store containing features which are values calculated from raw data. For example, average monthly cost of some activity or a statistical likelihood (z-score) that a financial transaction is fraudulent. A feature is pre-built data calculation usable by data scientists developing specific analytics processes or models. RedisAI enables models to be served where the features are stored thus, Redis Labs claims, improving AI-based application performance by an order of up to two orders of magnitude.
RedisRaft will be generally available with the release of Redis 7.0 in the second half of 2021.
The integration of RedisJSON and RediSearch is in private preview and will be generally available in the second half of 2021 with Active-Active support.
RedisAI, as an online feature store, is available today for on-premise deployments and will be available for Redis Enterprise Cloud in the second half of 2021.