Search

Makeroom

RegisterLogin

Discussion

General
Tech

Library

Chevron Right Icon
Design
Resources
Websites
Articles
Chevron Right Icon
Web development
Cool Libraries
Tools
Resources
Papers and Studies
Articles
Language Models
Tech and Systems
Chevron Right Icon
Computers
Chevron Right Icon
Windows Tools and Modding
Windhawk
Raycast for Windows
Rainmeter
Plasma 6.7
Haiku: BeOS-Inspired Open-Source OS
Chevron Right Icon
Random fun stuff
Esoteric File Systems
Cool websites
Chevron Right Icon
Friends
Unity - Cheaterman's Bar
ChatGPT
Gentoo is Rice - Humor about Linux Obsession
Chevron Right Icon
Storyden
Selfh.st
OpenAlternative
Microlaunch
Peerlist
Glama.ai
AlternativeTo
Brandfetch
Dokploy
PitchHut
Piefed Social
 Collections Links Members Roles

Makeroom

Icon

A small rag-tag assortment of makers, engineers and designers sharing mentoring, support and projects to work on at any stage in their career.

Join our Discord server!


Welcome to the Makeroom installation of Storyden!

This acts as a live demo of Storyden's forum and library software. On this site you'll find a curated collection of web and design resources as well as anything our members share.

Feel free to participate, this may be a demo but it's never wiped. That being said, Storyden is in active development and we encourage you to experiment respectfully as well as report any security issues you find to @Southclaws or by opening an issue.

Have an amazing day!

powered by storyden

Login
Library
your-distributed-system-is-slower-than-a-laptop

No versions or drafts yet.

Your Distributed System Is Slower Than a Laptop

Lloyd Moore’s deep dive into the economic and performance reality of distributed systems in 2026. The article argues that the industry’s default-to-distributed reflex—formed when hardware constraints required it—persists even though modern servers have 192 cores, 24TB memory, and SSDs reading 14GB/s. He shows how most companies pay millions in coordination overhead to parallelize their own infrastructure, not their workload.

Moore walks through a concrete example: a SaaS company’s .4M distributed event pipeline (Kafka, Flink, platform engineers) processing 2 billion events a day—which is a single-machine workload with a hundredfold capacity margin. A competent two-server setup would cost 7K/year and be faster.

The core argument: distribution is a cost to be justified by measurement, not a default justified by convention. Before approving any distributed architecture, someone should build the single-machine baseline and prove the distributed system beats it by enough margin to justify the operating costs. Most won’t.

A must-read for anyone designing systems at scale or defending architectural choices in design reviews.

Your Distributed System Is Slower Than a Laptop

In 2015 a single thread on a laptop beat 128 cores at graph processing. A decade on, companies still pay seven figures a year to parallelise their own overhead. The one-week measurement that would catch it is missing from almost every design review.

codegood.co