This paper prepared by ETH Zürich was published on Arxiv.
Abstract
FaaS (Function-as-a-Service) brought a fundamental shift into cloud computing: (persistent) virtual machines have been replaced with dynamically allocated resources, trading locality and statefulness for a pay-as-you-go model more suitable for varying and infrequent workloads. However, adapting services to functions in the serverless paradigm while still fulfilling functional requirements is challenging. In this work, we demonstrate how ZooKeeper, a centralized coordination service that offers a safe and wait-free consensus mechanism, can be redesigned to benefit from serverless computing. We define synchronization primitives to extend the capabilities of scalable cloud storage and contribute a set of requirements for efficient and scalable FaaS computing. We introduce FaaSKeeper, the first coordination service built on serverless functions and cloud-native services, and share serverless design lessons based on our experiences of implementing a ZooKeeper model deployable to clouds today. FaaSKeeper provides the same consistency guarantees and interface as ZooKeeper, with a serverless price model that lowers costs up to 450 times on infrequent workloads.
Authors
Marcin Copik, Alexandru Calotoiu, Konstantin Taranov, Torsten Hoefler, (ETH Zürich)