Cluster as a Service: A Container Based Cluster Sharing Approach with Multi-user Support
Authors:
- Wei CuiWCWei Cui
- Hanglong ZhanHZHanglong Zhan
- Bao LiBLBao Li
- Hu WangHWHu Wang
- Donggang CaoDCDonggang Cao
- 1 March 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 111-118
Abstract
With the rapid development of cloud computing and big data processing, more and more application frameworks are being considered to run in "cloud way". This brings about several challenges to the cloud computing platform, e.g., being able to run most existing heterogeneous applications, providing scalability and elasticity support for newly emerged frameworks, and most importantly, sharing cluster resources effectively. In this paper, we propose a new service model that is suitable for medium and small-sized data center to solve these problems in a relatively easy and general way - ClaaS (Cluster as a Service). The idea is virtualizing the cluster environment for application frameworks. Most applications can directly run in the virtual cluster environment without any modification, which is a great advantage. Based on lightweight containers, we implement a real system of ClaaS named Docklet in order to prove the feasibility of this service model. In the meantime, we preliminarily design the definition of applications to make them easy to deploy. Finally, we present several examples and evaluate the whole system.Keywords
This publication has 7 references indexed in Scilit:
- Container-Based Orchestration in Cloud: State of the Art and Challenges2015
- The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines, Second editionSynthesis Lectures on Computer Architecture, 2013
- ViteraaS: Virtual Cluster as a Service2011
- OpenNebula: A Cloud Management ToolIEEE Internet Computing, 2011
- Technical perspectiveCommunications of the ACM, 2008
- DSC: scheduling parallel tasks on an unbounded number of processorsIEEE Transactions on Parallel and Distributed Systems, 1994
- A bridging model for parallel computationCommunications of the ACM, 1990