Scylla Shard-per-Core Architecture

Scylla’s revolutionary new approach to NoSQL database architecture is optimized for modern hardware and cloud compute

A simplified depiction of Scylla’s shard-per-core design, with the read path on the top, and the write path below.

Scylla, the real-time big data NoSQL database, built from the ground up in C++ with the full knowledge and experience of how to take advantage of modern multicore, multi-processor NUMA server hardware and fundamental features of the Linux operating system. Scylla is a massively-parallelized database engine that runs sharded on each core in your server, across all the servers in a cluster. Its design enables Scylla to run millions of operations per second at sub-millisecond average latencies.

Each node in a Scylla cluster operates peer-to-peer; there is no primary/replica model to create bottlenecking or single points of failure. Within each node data is sharded per-core.

Modern Shared-Nothing Architecture

Scylla uses a highly asynchronous, shared-nothing design, based on its underlying Seastar framework. Each shard of data is allotted CPU, RAM, persistent storage and networking resources which it uses as efficiently as possible. With its own custom schedulers for CPU and I/O processing, Scylla knows how to get maximum efficiency out of your Big Data infrastructure.

Scylla University

Get started on the path to Scylla expertise.

Live Test

Spin up a 3-node Scylla cluster to see our light-speed performance

Virtual Workshop

Interactive sessions with our NoSQL solution architects.