Posted on

Benchmarking AWS Graviton2 and gp3 Support for Apache Kafka

With the release of AWS’s Graviton2 (ARM) instances and gp3 disks, I immediately wanted to explore the potential opportunity for anyone using Apache Kafka. My team and I embarked on a journey to understand the changes required for Kafka users to be able to provision AWS Graviton2 instances paired with gp3 disks.  

Previously we’d only used Java 11 (OpenJDK) to run the Kafka service on x86 instances. As part of this change, we also shifted our internal environment to use Amazon Corretto. Amazon Corretto is used internally by AWS; it has built-in performance enhancements, security fixes, and is compatible with Java SE standards. Furthermore, Amazon Corretto reportedly has a performance benefit over OpenJDK distributions when operating in ARM architecture especially for network-intensive applications, of which Kafka is one. 

Posted on

C++ Memory Model: Migrating From X86 to ARM

Over the past years, we have seen a shift in processors from the previously dominant x86 architecture to the more energy-efficient (and often cheaper) ARM architecture. This trend is true for both consumer hardware, e.g., Apple's M1 SoC, and also server hardware, e.g. AWS's Gravitron processor. Given that the ARM architecture has a more relaxed memory model, this might have some subtle impact on C++ programs.

So far, ArangoDB was only built for x86-based CPUs, but due to the rise of ARM processors, we are faced with an ever-increasing number of requests from users to support ARM. Since performance is at the heart of ArangoDB, there are a lot of places where we use atomic operations. In order to ensure that our code behaves correctly on ARM, we have to revisit all those places and make sure that the operations use the correct memory order. But what does that mean?