Lambdata: Optimizing Serverless Computing by Making Data Intents Explicit
Yang Tang, Junfeng Yang
Abstract
Serverless computing emerges as a new paradigm to build cloud applications, in which developers write small functions that react to cloud infrastructure events, and cloud providers maintain all resources and schedule the functions in containers. Serverless computing thus enables developers to focus on their core business logic and leave server management and scaling to cloud providers. Unfortunately, existing serverless computing systems suffer from a key limitation that deprives them of enjoying significant speedups. Specifically, they treat each cloud function as a black box and are blind to which data the function reads or writes, therefore missing potentially huge optimization opportunities, such as caching data and colocating functions. We present Lambdata, a novel serverless computing system that enables developers to declare a cloud function's data intents, including both data read and data written. Once data intents are made explicit, Lambdata performs a variety of optimizations to improve speed, including caching data locally and scheduling functions based on code and data locality. Our evaluation of Lambdata shows that it achieves an average speedup of 1.51x on the turnaround time of practical workloads and reduces monetary cost by 16.5%.