Architecting Low-Latency Java Systems at Massive Scale

Java dominates enterprise deployments, but low-latency scenarios are still a challenge. Think of credit card authorization, mobile sessions handling, electronic trading as of typical examples that have to process thousands of operations per second within sub-millisecond boundaries.

Due to the nature of garbage collectors, Java can initiate a stop-the-world pause at any moment in time breaking low-latency requirements and making the behavior of the whole system unpredictable. That's, primarily, why Java is not seen as a viable option for such workloads by many.

In this session, we're going to review a Java-powered software stack based on Azul Zing and Apache Ignite that makes JVM behavior predictable, scales out linearly, and allows selecting Java for high-throughput low-latency scenarios.

BIO

Simon Ritter is the Deputy CTO of Azul Systems and Java Champion. Simon has been in the IT business since 1984 and holds a Bachelor of Science degree in Physics from Brunel University in the U.K. Simon joined Sun Microsystems in 1996 and started working with Java technology from JDK 1.0; he has spent time working in both Java development and consultancy. Having moved to Oracle as part of the Sun acquisition, he managed the Java Evangelism team for the core Java platform. Now at Azul, he continues to help people understand Java as well as Azul’s JVM technologies and products. Simon has twice been awarded Java Rockstar status at JavaOne and currently represents Azul on the JCP Executive Committee and on the Java SE Expert Group.

Denis Magda is an open-source software enthusiast who started his journey in the technology evangelism group of Sun Microsystems and Java engineering team of Oracle. He now supports the Apache Software Foundation in the roles of Apache Ignite committer and Project Management Committee member. As the Head of Developer Relations for GridGain Systems, he works with software engineers and architects to help them gain expertise in in-memory computing