Using Platform Engineering Concepts to Tune Java Systems

The role of the infrastructure engineers and software developers is very well understood in the industry; however, what happens in the exchanges between these two schools of thought during critical design and implementation phases of projects are often misunderstood in the industry. Now, in order to move towards the next era of Java platform designs and implementations, one should fully understand the nature of this problem by acknowledging the following fact: it is true that half of the world's new Java applications miss their SLA, and almost all of these applications have 2.x over-provisioned hardware. Such cost is deeply hurting our industry, and when CIOs are being told that in 3 to 5 years' time most of them want to be out of the “infrastructure business”, most CIOs seem to think that by getting away from the “infrastructure business” then somehow magically the 2.x hardware over-provisioning problem will also disappear. This is not true, and platform engineering is the exact remedy needed to fix this industry. Attend this session to learn about how new industry and skill-sets are being formed around platform engineering concepts, initially in the session we showcase this industry gap and how to best fill it, but then we quickly move towards showing an actual recent example of how to apply platform engineering concepts to refine a design. The era of platforms is upon-us, from the Third Platform, Cloud Native Apps, Microservices, Virtualization, and to Containers are all key platforming concepts completing the platform engineering story.

In this session we cover various aspects of these platforming technologies, and specifically deep dive into GC tuning techniques and how to best build platform engineered systems; in particular, the focus will be on tuning large scale JVM deployments. Come to this session to learn about GC tuning recipe that can give you the best configuration for latency sensitive applications. While predominantly most enterprise class Java workloads can fit into a scaled-out set of JVM instances of less than 4GB JVM heap, there are workloads in the in memory database space that require fairly large JVMs. We will look at various Java platform scales, some holding a few large JVMs of 90GB heap space, while other platforms are of thousands of JVM instances of less than 4GB heap space on each. We also inspect the extreme vertical scalability the JVM by looking at a recent 360GB JVM that we worked on.

About Emad Benjamin

Emad has spent the past 25 years in various software engineering positions involving software development of application platforms and distributed systems for various industries such as finance, health, IT, and heavy industry – in various international locations. Emad is currently the Sr. Director and Chief Technologist of Application Platforms with Office of the CTO at VMware, focusing on building hybrid cloud distributed runtimes that are application aware.

More About Emad »