All posts by Roman Gershman
Dragonfly's New Sorted Set Implementation
This blog post delves into Dragonfly's innovative approach to enhancing the sorted set data type, showcasing a new B+ tree implementation that significantly reduces memory usage by up to 40% and improves performance.
The Unbearable Lightness of Horizontal Scaling
This post explores the limitations of horizontal scaling in terms of cluster reliability, load distribution, and cloud over-commitment. It also outlines design decisions that were made to allow Dragonfly, a drop-in Redis replacement, to scale vertically in order to handle heavy workloads and large data volumes on a single instance. By adopting Dragonfly's vertical scaling capabilities, organizations can achieve improved performance, cost savings, and operational efficiency in their distributed systems.
Announcing the Kubernetes Operator for Dragonfly
We are thrilled to announce the latest addition to our in-memory data store - the Kubernetes operator for Dragonfly!
Redis vs. Dragonfly Scalability and Performance
A thorough benchmark comparison of throughput, latency, and memory utilization between Redis and Dragonfly.
DragonflyDB 2022 In Review
2022 saw the emergence of a new technology and database project, Dragonfly, as well as the founding of a new company (DragonflyDB) to shepherd and evolve it.
Balanced vs Unbalanced
Balance is essential in life. When our focus is limited to improving a single aspect of our life, we weaken the whole system.
Infrastructure should be boring
Infrastructure should be boring. Boring is good. Boring means that it just works, and you don’t have to worry about it. A year ago, we went on a quest to build a boring in-memory store.
10k Stars
Dragonfly crossed the 10K GitHub stars milestone in just 75 days. What an incredible start for our journey!
Dragonfly Cache Design
I talked in my previous post about Redis eviction policies. In this post, I would like to describe the design behind Dragonfly cache.
Redis Analysis - Part 2: Simplicity
Let’s talk about the simplicity of Redis. Redis was initially designed as a simple store, and it seems that its APIs achieved this goal.
Redis Analysis - Part 1: Threading model
Following my previous post, we are going start with the “hottest potato” - single-threaded vs multi-threaded argument.
A prelude to analysis of Redis memory-store
During the last 13 years, Redis has become a truly ubiquitous memory store that has won the hearts of numerous dev-ops and software engineers.