Performance testing Java Applications

Every so often, you’ll read a performance benchmark (of a Java or other application), with bold claims for how well X performs compared to Y. Testing the performance of your Java application is an artform rather than engineering and is a minefield of misconceptions, misunderstanding, and misinformation. In this session, we will review the basics and give you concrete steps to build a robust performance testbed for your application. We will be looking at this from a real-world server-side application point of view, specifically for Java apps. We’ll review common problems and how to avoid them. We’ll cover these topics while building up a performance test and running it live:

* Define your goals: SLA, latency, throughput, stability
* Test env vs. Production env for testing
* The impact of GC on Java app performance
* Tools for setting up, driving load, and getting perf test results
* Testing application infrastructures like Kafka, Spark, and Cassandra
* Operating system settings, JVM settings, memory sizing, and CPU sizing
* Analyzing perf test results and finding bottlenecks that are both apparent and not obvious

Speaker
Pratik Patel is a Java Champion and developer advocate at Azul Systems. He wrote the first book on 'enterprise Java' in 1996, "Java Database Programming with JDBC." An all-around software and hardware enthusiast with experience in the healthcare, telecom, financial services, and startup sectors. Helps to organize the Atlanta Java User Group, is a frequent speaker at tech events, and master builder of nachos.