Inverse Queuing Model-Based Feedback Control for Elastic Container Provisioning of Web Systems in Kubernetes

Container orchestration platforms such as Kubernetes and Kubernetes-derived KubeEdge (called Kubernetes-based systems collectively) have been gradually used to conduct unified management of Cloud, Fog, and Edge resources. Container provisioning algorithms are crucial to guaranteeing quality of services (QoS) of such Kubernetes-based systems. However, most existing algorithms focus on placement and migration of fixed number of containers without considering elastic provisioning of containers. Meanwhile, widely used linear-performance-model-based feedback control or fixed-processing-rate-based queuing model on diverse platforms cannot describe the performance of containerized Web systems accurately. Furthermore, a fixed reference point used by existing methods is likely to generate inaccurate output errors incurring great fluctuations encountered with large arrival-rate changes. In this article, a feedback control method is designed based on a combination of varying-processing-rate queuing model and linear-model to provision containers elastically which improves the accuracy of output errors by learning reference models for different arrival rates automatically and mapping output errors from reference models to the queuing model. Our approach is compared with several state-of-art algorithms on a real Kubernetes cluster. Experimental results illustrate that our approach obtains the lowest percentage of service level agreement (SLA) violation (decreasing no less than 8.44 percent) and the second lowest cost.

[1]  Moustafa Ghanem,et al.  Elastic Application Container: A Lightweight Approach for Cloud Resource Provisioning , 2012, 2012 IEEE 26th International Conference on Advanced Information Networking and Applications.

[2]  Lui Sha,et al.  Queueing model based network server performance control , 2002, 23rd IEEE Real-Time Systems Symposium, 2002. RTSS 2002..

[3]  Omer F. Rana,et al.  Feedback-Control & Queueing Theory-Based Resource Management for Streaming Applications , 2017, IEEE Transactions on Parallel and Distributed Systems.

[4]  Isis Truck,et al.  From Data Center Resource Allocation to Control Theory and Back , 2010, 2010 IEEE 3rd International Conference on Cloud Computing.

[5]  Sang Hyuk Son,et al.  Feedback Control Architecture and Design Methodology for Service Delay Guarantees in Web Servers , 2006, IEEE Transactions on Parallel and Distributed Systems.

[6]  Ofer Biran,et al.  VM Placement Strategies for Cloud Scenarios , 2012, 2012 IEEE Fifth International Conference on Cloud Computing.

[7]  Gang Wang,et al.  An autonomic provisioning framework for outsourcing data center based on virtual appliances , 2008, Cluster Computing.

[8]  Jinjun Chen,et al.  Authorized Public Auditing of Dynamic Big Data Storage on Cloud with Efficient Verifiable Fine-Grained Updates , 2014, IEEE Transactions on Parallel and Distributed Systems.

[9]  Philippe Merle,et al.  Elasticity in Cloud Computing: State of the Art and Research Challenges , 2018, IEEE Transactions on Services Computing.

[10]  Luciano Baresi,et al.  A discrete-time feedback controller for containerized cloud applications , 2016, SIGSOFT FSE.

[11]  I. Ahmad,et al.  Machine learning-based auto-scaling for containerized applications , 2019, Neural Computing and Applications.

[12]  Hervé Paulino,et al.  QoE-aware auto-scaling of heterogeneous containerized services (and its application to health services) , 2020, SAC.

[13]  Marin Litoiu,et al.  Scalable adaptive web services , 2008, SDSOA '08.

[14]  Yixin Diao,et al.  Feedback Control of Computing Systems , 2004 .

[15]  Wei Zhao,et al.  Migration Modeling and Learning Algorithms for Containers in Fog Computing , 2019, IEEE Transactions on Services Computing.

[16]  Gregory R. Ganger,et al.  Stratus: cost-aware container scheduling in the public cloud , 2018, SoCC.

[17]  Enda Barrett,et al.  Applying reinforcement learning towards automating resource allocation and application scalability in the cloud , 2013, Concurr. Comput. Pract. Exp..

[18]  Dejun Mu,et al.  Feedback Control-Based QoS Guarantees in Web Application Servers , 2008, 2008 10th IEEE International Conference on High Performance Computing and Communications.

[19]  Jun Han,et al.  A multi-model framework to implement self-managing control systems for QoS management , 2011, SEAMS '11.

[20]  Ang Gao,et al.  A Self-Tuning Control for Web QoS , 2009, 2009 International Conference on Information Engineering and Computer Science.

[21]  Richard O. Sinnott,et al.  Auto-Scaling a Defence Application across the Cloud Using Docker and Kubernetes , 2018, 2018 IEEE/ACM International Conference on Utility and Cloud Computing Companion (UCC Companion).

[22]  Srikumar Venugopal,et al.  Using reinforcement learning for controlling an elastic web application hosting platform , 2011, ICAC '11.

[23]  Fangxiong Xiao,et al.  Dynamic deployment of virtual machines in cloud computing using multi-objective optimization , 2014, Soft Computing.

[24]  Christoph Hochreiner,et al.  Elastic Provisioning of Virtual Machines for Container Deployment , 2017, ICPE Companion.

[25]  Luiz Fernando Bittencourt,et al.  Towards Virtual Machine Migration in Fog Computing , 2015, 2015 10th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (3PGCIC).

[26]  Songyun Wang,et al.  Auto scaling virtual machines for web applications with queueing theory , 2016, 2016 3rd International Conference on Systems and Informatics (ICSAI).

[27]  Tridib Mukherjee,et al.  SCoPe: A Decision System for Large Scale Container Provisioning Management , 2016, 2016 IEEE 9th International Conference on Cloud Computing (CLOUD).

[28]  Jordi Vilaplana,et al.  A queuing theory model for cloud computing , 2014, The Journal of Supercomputing.

[29]  Yifei Lu,et al.  Unequal‐interval based loosely coupled control method for auto‐scaling heterogeneous cloud resources for web applications , 2020, Concurr. Comput. Pract. Exp..

[30]  Jie Lu,et al.  Optimal Cloud Resource Auto-Scaling for Web Applications , 2013, 2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing.

[31]  Sherali Zeadally,et al.  Container-as-a-Service at the Edge: Trade-off between Energy Efficiency and Service Availability at Fog Nano Data Centers , 2017, IEEE Wireless Communications.

[32]  Rajarshi Das,et al.  A Hybrid Reinforcement Learning Approach to Autonomic Resource Allocation , 2006, 2006 IEEE International Conference on Autonomic Computing.

[33]  Waheed Iqbal,et al.  Containers vs Virtual Machines for Auto-scaling Multi-tier Applications Under Dynamically Increasing Workloads , 2018, INTAP.

[34]  Carlos Juiz,et al.  Genetic Algorithm for Multi-Objective Optimization of Container Allocation in Cloud Architecture , 2017, Journal of Grid Computing.

[35]  Cheng-Zhong Xu,et al.  Model Predictive Feedback Control for QoS Assurance in Webservers , 2008, Computer.

[36]  Rajkumar Buyya,et al.  A Cost-Efficient Container Orchestration Strategy in Kubernetes-Based Cloud Computing Infrastructures with Heterogeneous Resources , 2020, ACM Trans. Internet Techn..

[37]  Khaled Salah,et al.  epcAware: A Game-Based, Energy, Performance and Cost-Efficient Resource Management Technique for Multi-Access Edge Computing , 2020, IEEE Transactions on Services Computing.