Accelerating Serverless Computing by Harvesting Idle Resources
Accelerating Serverless Computing by Harvesting Idle Resources
复制标题
DOI：
10.1145/3485447.3511979
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Hanfei Yu;Hao Wang;Jian Li;Xuemei Yuan;Seung-Jong Park
中科院分区：
文献类型：
--
作者：
Hanfei Yu;Hao Wang;Jian Li;Xuemei Yuan;Seung-Jong Park
无服务器计算可实现细粒度资源扩展的自动化，并通过无状态功能简化在线服务的开发和部署。然而，由于不同的函数类型、依赖关系和输入大小，用户分配适当的资源仍然很重要。资源分配的错误配置会导致功能配置不足或配置过多，并导致资源利用率持续较低。本文介绍了 Freyr，这是一种适用于无服务器平台的新型资源管理器 (RM)，它通过从过度配置的功能到配置不足的功能动态收集闲置资源来最大限度地提高资源效率。 Freyr 实时监控每个功能的资源利用率，检测过度配置和配置不足，并通过应用深度强化学习算法和保护机制来学习安全地收集闲置资源并有效地加速功能。我们在 13 节点 Apache OpenWhisk 集群中实现并部署了 Freyr 原型。实验结果表明，38.8%的函数调用有Freyr收获的闲置资源，39.2%的调用因收获的资源而加速。与基线 RM 相比，Freyr 将 99% 功能响应延迟减少了 32.1%。
Serverless computing automates fine-grained resource scaling and simplifies the development and deployment of online services with stateless functions. However, it is still non-trivial for users to allocate appropriate resources due to various function types, dependencies, and input sizes. Misconfiguration of resource allocations leaves functions either under-provisioned or over-provisioned and leads to continuous low resource utilization. This paper presents Freyr, a new resource manager (RM) for serverless platforms that maximizes resource efficiency by dynamically harvesting idle resources from over-provisioned functions to under-provisioned functions. Freyr monitors each function’s resource utilization in real-time, detects over-provisioning and under-provisioning, and learns to harvest idle resources safely and accelerates functions efficiently by applying deep reinforcement learning algorithms along with a safeguard mechanism. We have implemented and deployed a Freyr prototype in a 13-node Apache OpenWhisk cluster. Experimental results show that 38.8% of function invocations have idle resources harvested by Freyr, and 39.2% of invocations are accelerated by the harvested resources. Freyr reduces the 99th-percentile function response latency by 32.1% compared to the baseline RMs.