Dragonfly

All posts by Roman Gershman

cover

Dragonfly Cloud vs. AWS ElastiCache: Product Breakdown

Compare the differences between Dragonfly Cloud and AWS ElastiCache, focusing on pricing, performance, scalability, and unique features to optimize your in-memory data store needs.

cover

Dragonfly's New Sorted Set Implementation

This blog post dives 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.

cover

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.

cover

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!

cover

Redis vs. Dragonfly Scalability and Performance

Comparing throughput, latency, and memory utilization benchmarks between Redis and Dragonfly.

cover

DragonflyDB 2022 In Review

In 2022, a new technology and database project, Dragonfly, emerged, alongside the founding of DragonflyDB to shepherd and evolve it.

cover

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.

cover

Infrastructure should be boring

How we have built a boring infrastructure that everyone is excited about

cover

10k Stars

Dragonfly crossed the 10K GitHub stars milestone in just 75 days.

cover

Dragonfly Cache Design

The design behind Dragonfly cache

cover

Redis Analysis - Part 2: Simplicity

What simplicity means to you as a datastore user?

cover

Redis Analysis - Part 1: Threading model

Single-threaded vs Multi-threaded

cover

A prelude to analysis of Redis memory-store

Will Redis stay competitive in a few years without reinventing itself?