Elastic Provisioning of Virtual Machines for Container Deployment

Docker containers enable to package an application together with all its dependencies and easily run it in any environ- ment. Thanks to their ease of use and portability, containers are gaining an increasing interest and promise to change the way how Cloud platforms are designed and managed. For their execution in the Cloud, we need to solve the container deployment problem, which deals with the identification of an elastic set of computing machines that can host and execute those containers, while considering the diversity of their requirements. In this paper, we provide a general formulation of Elastic provisioning of Virtual machines for Container Deployment (for short, EVCD) as an Integer Linear Programming prob- lem which takes explicitly into account the heterogeneity of container requirements and of virtual machine resources. Beside optimizing multiple QoS metrics, EVCD can reallocate containers at runtime, if a QoS improvement can be achieved. We evaluate the proposed formulation by comparing it with two well-known heuristics, i.e., greedy first-fit and round-robin, which are usually adopted for solving the deployment problem.
 @inproceedings{nardelli2017acpross,
  author = {Nardelli, Mattheo and Hochreiner, Christoph and Schulte, Stefan},
  title = {Elastic Provisioning of Virtual Machines for Container Deployment},
  booktitle = {International Workshop on Autonomous Control for Performance and Reliability Trade-Offs in Internet of Services (ACPROSS 2017) at 8th ACM/SPEC International Conference on Performance Engineering (ICPE 2017)},
  year = {2017},
  pages = {5--10}
}