无服务器平台资源调度综述

Survey of Resource Scheduling for Serverless Platforms

无服务器(Serverless)计算正成为部署云应用程序的一种具有广阔发展前景的范式。其实现了一种真正的现收现付的计费方式,并且不会浪费资源。开发人员无需担心计算平台的底层细节,只需在处理请求或事件时付费,从而降低了开发人员的门槛。无服务器模式的转变虽然带来了机遇,但也带来了平台函数冷启动延迟、资源利用不足等问题。为此,文中对无服务器计算平台的资源调度技术做了深入的调查和分析,重点阐述了面向资源利用、响应时间延迟以及多目标优化的无服务器平台资源调度的技术原理和相关研究现状,并在此基础上分析总结并指明了无服务器平台资源调度未来的主要研究方向:即面向不同应用类型负载的调度优化、响应时间与资源利用率的折衷调度、虚拟机与无服务器平台的联合调度以及无服务器资源调度的混合算法。

Serverless computing is emerging as a promising paradigm for deploying cloud applications.It really implements pay-as-you-go billing without wasting resources.Developers don’t have to worry about the low-level details of the computing platform,they just need to pay when processing requests or events,thus lowering the threshold for developers.Although the change of serverless model brings opportunities,it also brings problems such as cold startup delay of platform function and insufficient resource utilization.Therefore,this paper makes an in-depth investigation and analysis of the resource scheduling technology of the serverless computing platform.The technical principle and research status of resource scheduling in serverless platform based on resource utilization,response time delay and multi-objective optimization are discussed.Finally,this paper points out the trends of future research directions:scheduling for different application types,the tradeoff between response time and resource utilization,joint scheduling between virtual machine and serverless platform,and hybrid algorithm for serverless resource scheduling.