FIAless: Asynchronous Programming for Large-Scale Burst Requests in Serverless Computing

As emerging microservice hosting platforms, serverless computing platforms are highly favour for their simplicity and high level of automation when deploying and running stateless functions. However, when any number of users sends many simultaneous requests to one or more functions, the frequent synchronization between stateless functions and remote storage can lead to high latency and additional system overhead during the request execution process on serverless platforms. In this paper, we design a concurrent scheduling policy called "Function in Asynchronous Serverless" (FIAless), which is based on asynchronous input/output (I/O), to handle large-scale burst requests on serverless platforms. FIAless breaks down the request execution process into subtasks with different execution characteristics and optimizes the scheduling and resource allocation schemes of each subtask to reduce the end-to-end latency and improve the overall performance of the system. In addition, FIAless monitors the entire lifecycle of each running request, ensuring that suspended requests can be promptly resumed. Finally, FIAless also periodically processes the residual data contained in memory after the operation execution procedure to promptly release resources. We evaluate FIAless by running multiple serverless computing benchmarks on Knative. Compared with running on the original Knative platform, the average request execution time is reduced by 61%, the memory consumption level is decreased by 80%, and high CPU utilization and low latency rates are maintained.