Abstract

Serverless computing allows developers to create workflows for complex tasks through the composition of serverless functions. Current serverless workflow engines rely on master-side patterns which hinder the interaction between serverless functions, causing performance issues. In this paper, a decentralized worker-side pattern is proposed that provides enhanced performance by allowing each workflow function to schedule itself from the current node to the next without having to interact with the master controller. It treats the serverless workflow as a whole unit and uses a locality strategy to optimize performance. A new high-performance workflow engine called BriskChain has been implemented to demonstrate the effectiveness of this approach. Experiments on a real-world application show that BriskChain is able to achieve 2.5 times better performance than a state-of-the-art serverless workflow engine.