Latency: Reduce Delay in Software Systems

From first principles to production-ready code, Latency teaches you how to make your software faster at every layer of the stack. You'll learn what latency really is, how it differs from bandwidth, and why it matters for user experience. Then, guided by practical examples, you'll apply Little's Law, design lock-free algorithms, and architect caching systems that scale. You'll discover how your code runs differently on distributed systems, databases, and operating systems, and understand the common latency-causing issues in each situation.

In Latency you'll learn how to:

- Define latency, distinguish it from bandwidth, and understand its impact on user experience
- Model performance with Little's Law and Amdahl's Law, then measure and visualize delays
- Optimize data access with colocation, replication, partitioning, and caching
- Accelerate logic with algorithmic improvements, memory tuning, and lock-free concurrency
- Minimize delays with asynchronous processing, predictive techniques, and speculative execution

Put simply, latency is the delay between a cause and effect. In practice, too much latency can create problems throughout a software system, ranging from inaccurate calculations and timeouts to impatient users simply abandoning your applications. Latency issues can be challenging to avoid and troubleshoot. This book balances theory with practical implementations, turning academic research into useful techniques you can apply to your projects.

About the technology

From lost microseconds routing server messages to page loads that keep users waiting, latency can kill good software. This one-of-a-kind book shows you how to spot, understand, and fix unwanted latency in your applications and infrastructure.

About the book

Latency: Reduce delay in software systems shows you how to troubleshoot latency in existing applications and create low latency systems from the ground up. In it, you'll discover high-impact fixes for measuring latency and advanced optimizations in memory management, concurrency models, and predictive execution. The tips and tricks, hands-on projects, and personal insights make this book as enjoyable as it is practical.

What's inside

- How to model and measure latency
- Organizing application data for low latency
- Accelerating your code
- Hiding latency

About the reader

For software engineers with a working knowledge of backends. Examples in Rust.

About the author

Pekka Enberg has experience in operating systems, databases, and distributed systems, having worked on the Linux kernel and the Scylla and Turso databases.

Table of Contents

Part 1
1 Introduction
2 Modeling and measuring latency
Part 2
3 Colocation
4 Replication
5 Partitioning
6 Caching
Part 3
7 Eliminating work
8 Wait-free synchronization
9 Exploiting concurrency
Part 4
10 Asynchronous processing
11 Predictive techniques
A Further reading