DRS: A deep reinforcement learning enhanced Kubernetes scheduler for microservice-based system

doi:10.1002/spe.3284

	DRS: A deep reinforcement learning enhanced Kubernetes scheduler for microservice-based system
	Jian, Zhaolong 1; Xie, Xueshuo 1,2; Fang, Yaozheng 1; Jiang, Yibing 1; Lu, Ye 3; Dash, Ankan 4; Li, Tao 1,2; Wang, Guiling 4
	2023-10-25
发表期刊	SOFTWARE-PRACTICE & EXPERIENCE
ISSN	0038-0644
页码	25
摘要	Recently, Kubernetes is widely used to manage and schedule the resources of microservices in cloud-native distributed applications, as the most famous container orchestration framework. However, Kubernetes preferentially schedules microservices to nodes with rich and balanced CPU and memory resources on a single node. The native scheduler of Kubernetes, called Kube-scheduler, may cause resource fragmentation and decrease resource utilization. In this paper, we propose a deep reinforcement learning enhanced Kubernetes scheduler named DRS. We initially frame the Kubernetes scheduling problem as a Markov decision process with intricately designed state, action, and reward structures in an effort to increase resource usage and decrease load imbalance. Then, we design and implement DRS mointor to perceive six parameters concerning resource utilization and create a thorough picture of all available resources globally. Finally, DRS can automatically learn the scheduling policy through interaction with the Kubernetes cluster, without relying on expert knowledge about workload and cluster status. We implement a prototype of DRS in a Kubernetes cluster with five nodes and evaluate its performance. Experimental results highlight that DRS overcomes the shortcomings of Kube-scheduler and achieves the expected scheduling target with three workloads. With only 3.27% CPU overhead and 0.648% communication delay, DRS outperforms Kube-scheduler by 27.29% in terms of resource utilization and reduces load imbalance by 2.90 times on average.
关键词	deep reinforcement learning Kubernetes scheduler microservice scheduling resource awareness
DOI	10.1002/spe.3284
收录类别	SCI
语种	英语
资助项目	This work is partially supported by the National Key Research and Development Program of China (2018YFB2100304), National Natural Science Foundation (62272248), the Open Project Fund of State Key Laboratory of Computer Architecture, Institute of Computing[2018YFB2100304] ; National Key Research and Development Program of China[62272248] ; National Natural Science Foundation[CARCH201905] ; National Natural Science Foundation[CARCHA202108] ; National Natural Science Foundation[2021KF0AB04] ; Open Project Fund of State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences[2022BKY028] ; Tianjin Graduate Scientific Research Innovation Project
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001087072100001
出版者	WILEY
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21100
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Tao
作者单位	1.Nankai Univ, Coll Comp Sci, Tianjin, Peoples R China 2.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing, Peoples R China 3.Nankai Univ, Coll Cyber Sci, Tianjin, Peoples R China 4.New Jersey Inst Technol, Dept Comp Sci, Newark, NJ USA
推荐引用方式 GB/T 7714	Jian, Zhaolong,Xie, Xueshuo,Fang, Yaozheng,et al. DRS: A deep reinforcement learning enhanced Kubernetes scheduler for microservice-based system[J]. SOFTWARE-PRACTICE & EXPERIENCE,2023:25.
APA	Jian, Zhaolong.,Xie, Xueshuo.,Fang, Yaozheng.,Jiang, Yibing.,Lu, Ye.,...&Wang, Guiling.(2023).DRS: A deep reinforcement learning enhanced Kubernetes scheduler for microservice-based system.SOFTWARE-PRACTICE & EXPERIENCE,25.
MLA	Jian, Zhaolong,et al."DRS: A deep reinforcement learning enhanced Kubernetes scheduler for microservice-based system".SOFTWARE-PRACTICE & EXPERIENCE (2023):25.