The IKEA Effect
On placing a higher value on things that you've either made yourself, or to which you’ve contributed towards making!
Peter Lawrey
16 articles
Optimise CPU Performance Through Isolation and System Tuning
Standard solutions for controlling CPU isolation for low-latency Linux applications are isolcpus and cgroups/csets. Each have their …
Unique Identifiers Based on Timestamps in Distributed Applications
Generate a highly efficient approach to generating an 8-byte lightweight identifier that is unique across many hosts.
Java is Very Fast, If You Don’t Create Many Objects
The cost of object creation can be far higher than the cost of cleaning them up if they are very short lived.
Using Pausers in Event Loops
Techniques that help maximise hardware utilisation, while also reducing power consumption, helping reduce costs to your organisation.
Approaches to Durability in Low Latency Messaging Queues
Is replicating data to a secondary system faster than sync-ing to disk? My first time benchmarking with a realistic example.
Event-Driven Order Processing Program
Following the Hello World example, this article looks at an Order Processor with a New Order Single in and an Execution Report out.
Efficient Memory Mapping for Terabyte Sparse Files in Java
Mapping large areas of memory avoids having to know in advance how much memory we need or having to resize the memory mappings while in use.
Event Driven Hello World Program
Let's use an event-driven Hello World (a paradigm where the flow is determined by events) to step through behaviour-driven development,
Behaviour Driven Development with Event Driven Architectures
How to use Behaviour Driven Development to establish the requirements from users, and Event Driven Architecture to automate testing!
"The More You Say, the Less People Remember...
…The Fewer the Words, the Greater the Profit.” And more wisdom and insight from Peter Lawrey, covering a range of development approaches.
How Does Kafka Perform When You Need Low Latency?
Kafka benchmarks aim to discuss low latency characteristics of Kafka. Instead, they appear to be configured for throughput rather than low …
Kafka vs. Chronicle for Microservices: Which is 750 Times Faster?
Find out why, while Kafka is a good choice for log aggregation, it might not be low latency enough for use cases involving microservices.
Unusual Java: StackTrace Extends Throwable
While having a class that directly extends Throwable is surprising, it is allowed and is also useful for providing additional information.
Low Latency Microservices, A Retrospective
Learn what we learned after five years of developing and supporting low latency microservices.
Storing 1TB in Virtual Memory on a 128GB Machine
Chronicle Queue and Chronicle Map allows you to have a persisted store which can be embedded into multiple JVMs on the same server.