ScyllaDB Engineering Resources

A Deep Dive into ScyllaDB’s Architecture

Take a technical deep dive into ScyllaDB's architecture and discover the "secret sauce" behind our high availability and superior performance.

Quantifying the Performance Impact of Shard-per-core Architecture

Most software isn’t architected to take advantage of modern hardware. How does a shard-per-code and shared-nothing architecture help – and exactly what impact can it make?

ScyllaDB Leaps Forward

Tablets: Rethinking Replication

Avi Kivity and Dor Laor AMA: “Tablets” replication, all things async, caching, object storage & more

Dor Laor and Avi Kivity discuss the new tablets replication algorithm (replacing Vnodes), ScyllaDB’s async shard-per-core architecture, strategies for tapping object storage with S3, the CDC...

Why ScyllaDB is Moving to a New Replication Algorithm: Tablets

How moving from vnode-based replication to tablets helps dynamically distribute data across the cluster, ultimately increasing ScyllaDB's elasticity.

Inside ScyllaDB’s Internal Cache

Why ScyllaDB completely bypasses the Linux cache during reads, using its own highly efficient row-based cache instead.

Topology on Raft: An Inside Look

ScyllaDB 6.0 completes the transition to strong consistency for all of the cluster metadata; learn what this means for users.

ScyllaDB’s Path to Strong Consistency: A New Milestone

In ScyllaDB 5.2, Raft is GA and used for the propagation of schema changes. Quickly assembling a fresh cluster, performing concurrent schema changes, updating node's IP addresses – all of this is...

What’s Next on ScyllaDB’s Path to Strong Consistency

What's next on ScyllaDB's path to strong consistency with Raft? Topology changes will be safe and fast: we won't be bound by ring delay any longer, and operator mistakes won't corrupt the cluster.

Clues in Long Queues: High IO Queue Delays Explained

How seemingly peculiar metrics might provide interesting insights into system performance

ScyllaDB Fast Forward: True Elastic Scale

Learn how our new tablets architecture enables new levels of elasticity, speed, simplicity, and efficiency -- dynamically redistributing data as the workload and topology evolve.

ScyllaDB’s Safe Topology and Schema Changes on Raft

How ScyllaDB is using Raft for all topology and schema metadata – and the impacts on elasticity, operability, and performance

How We Implemented ScyllaDB’s “Tablets” Data Distribution

How ScyllaDB implemented its new Raft-based tablets architecture, which enables teams to quickly scale out in response to traffic spikes

Smooth Scaling: Why ScyllaDB Moved to “Tablets” Data Distribution

The rationale behind ScyllaDB's new “tablets” replication architecture, which builds upon a multiyear project to implement and extend the Raft consensus protocol. It enables teams to quickly...

Retaining Database Goodput Under Stress with Per-Partition Query Rate Limiting

How we implemented ScyllaDB’s per-partition rate limit feature, which allows users to limit the rate of accepted requests on a per-partition basis, and the impact on “goodput”: the amount of...

Better “Goodput” Performance through C++ Exception Handling

Some very strange error reporting performance issues we uncovered while working on per-partition query rate limiting -- and how we addressed it through C++ exception handling.

ScyllaDB Drivers: Optimizing Performance

How ScyllaDB Drivers take advantage of the unique ScyllaDB architecture to deliver high performance and low latencies.