Scylla is presented as a highly available, scalable, performant NoSQL database. Scylla is generally used as a key-value store or wide-column model database.
Close-to-the-Hardware Design — Scylla uses an asynchronous, non-blocking design that takes advantage of modern hardware architecture. It provides throughput for taxing workloads.
Consistent, Low Latencies — Scylla’s underlying architecture enables it to deliver P99 latencies in the low single-digit milliseconds, even under extreme load. Maintenance operations do not slow performance.
Self-Optimizing — Scylla has a unified cache and self-optimizes its performance, removing complexity from the system. Written in C++, it does not require JVM tuning.
Highly Scalable — Scylla scales both horizontally and vertically. It can scale out to hundreds of nodes and its shard-per-core shared-nothing architecture scales up to take advantage of multi-core servers.
Low Total Cost of Ownership — Scylla makes full use of hardware infrastructure to minimize node count and reduce administrative overhead.
DBaaS — Scylla Cloud is a managed Database-as-a-Service (DBaaS). It runs on AWS and is certified for use in AWS Outposts, and now has a beta for GCP.
API Compatible with Apache Cassandra and Amazon DynamoDB