Abstract | ||
---|---|---|
It is a huge challenge to deploy a cloud computing system in large-scale data centers. In order to help resolve this issue, we propose an automatic cloud system deployment approach with the characteristics of reliability, availability, and load balance. Specifically, we use workflow to deal with the dependencies among the automatic deployment processes of a cloud system. We also design a failover mechanism to avoid the single point failure of the deployment server. Besides, we adopt a load balancing algorithm to solve the bottleneck problem of deploying a cloud system. We implement a prototype, and evaluate it with 16 physical nodes as well as a virtualized environment with 160 virtual machines. Experimental results show that the average deployment time under our approach is lower than that with traditional deployment methods. In addition, it achieves a cloud system deployment success ratio of up to 90﾿%, even in the high-concurrency environment. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-28430-9_6 | "CloudCom-Asia |
Field | DocType | Citations |
Failover,Single point of failure,Software deployment,Virtual machine,Computer science,Load balancing (computing),Real-time computing,Deployment diagram,Data center,Distributed computing,Cloud computing | Conference | 0 |
PageRank | References | Authors |
0.34 | 3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tao Xie | 1 | 5978 | 304.97 |
Haibao Chen | 2 | 41 | 5.05 |