Cracking the scalability wall

Length: 45 minutes

Room: Room 5

Abstract

In this talk, we’ll discuss a severe JVM performance issue, the methodology leading to its discovery, how it affects the whole Java ecosystem, and what you could do to avoid it in your code. This scalability bottleneck has existed in OpenJDK for decades; the most surprising aspect is how such an impactful problem has been undetected for so long, eluding existing diagnostic tooling, while many common idioms will trigger the issue. Chances are high that your code is affected as well. After explaining the issue, we’ll show some real-world code from popular OSS libraries and how we worked around the problem in several popular OSS Java libraries with simple, small changes, leading to significant efficiency improvements.

Day & time

Thursday, 1:00 – 1:45 PM

Intended audience

Java developers, or anyone running code on the JVM, who cares about performance, lowering operational costs, or carbon footprint of their service. The topic is fairly advanced but I'm going to try my best to make sure anyone who is familiar with Java idioms can understand what's going on.

• Sanne Grinovero

  Sanne Grinovero has been a member of the Hibernate team for about 15 years and contributed to many other OSS Java projects as well; among others he was a member of the R&D team creating Quarkus, Hibernate Search, Infinispan, Hibernate OGM, Hibernate Reactive. Deeply interested in performance and concurrency challenges around data access, scalability, and exploring integration with new storage technologies, distributed systems and search engines. He lived in Holland, Italy, the Caribbean Islands, Chile, Portugal and currently hacks in the countryside near London.

  

  SanneGrinovero