Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (8): 274-286.DOI: 10.3778/j.issn.1002-8331.2303-0543

• Big Data and Cloud Computing • Previous Articles     Next Articles

Active Microservice Fine-Grained Scaling Algorithm

PENG Kai, MA Fangling, XU Bo, GUO Jialu, HU Menglan   

  1. 1.Hubei Key Laboratory of Smart Internet Technology, School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China
    2.Hubei ChuTianYun Co., Ltd., Wuhan 430076, China
  • Online:2024-04-15 Published:2024-04-15

主动式微服务细粒度弹性缩放算法研究

彭凯,马芳玲,徐博,郭佳璐,胡梦兰   

  1. 1.华中科技大学 电子信息与通信学院 智能互联网技术湖北省重点实验室,武汉 430074
    2.湖北省楚天云有限公司,武汉 430076

Abstract: Microservice architecture has become the basic service architecture of cloud data center. However, the existing studies on the elastic scaling scheme of microservice systems are mostly based on horizontal scaling at the service or instance level, ignoring the fine-grained vertical scaling that can make full use of single server resources, resulting in resource waste. Therefore, an active microservice fine-grained elastic scaling algorithm is designed in this paper. The algorithm forecasts the request arrival rate to preconfigure the system resources. Based on the predicted results, the square root staffing rule is applied to calculate the number of required resources, and then the microservice is scaled by using the fine-grained resource control feature of vertical scaling and the high availability of horizontal scaling. Finally, an instance migration algorithm based on microservice dependency is applied to further reduce the resource overhead. Experimental results show that the proposed algorithm is effective in optimizing the delay and overhead of microservice systems.

Key words: microservice, instance deployment, gated recurrent unit, auto scaling, vertical and horizontal scaling

摘要: 微服务架构已成为云数据中心的基本服务架构。但目前关于微服务系统弹性缩放的研究大多是基于服务或实例级别的水平缩放,忽略了能够充分利用单台服务器资源的细粒度垂直缩放,从而导致资源浪费。为此,设计了主动式微服务细粒度弹性缩放算法。算法通过预测请求到达率对系统进行资源预配置。基于预测结果,应用平方根配置规则计算需求资源数量,进而利用垂直缩放的细粒度资源控制特性和水平缩放的高可用性对微服务进行伸缩。应用基于微服务依赖关系的实例迁移算法进一步降低资源开销。实验结果表明,提出的算法在优化微服务系统时延和开销方面取得了显著效果。

关键词: 微服务, 实例部署, 门控循环单元, 自动缩放, 垂直与水平扩展