Value-Based Allocation of Docker Containers

Abstract

Recently, an increasing number of public cloud vendors added Containers as a Service
\n(CaaS) to their service portfolio. This is an adequate answer to the growing popularity of Docker, a software technology allowing Linux containers to run independently on a host in an isolated environment. As any software can be deployed in a container, the nature of containers differs and thus assorted allocation and orchestration approaches are needed for their effective execution. In this paper, we focus on containers whose execution value for end users varies over time. A baseline and two dynamic allocation algorithms are proposed and compared with the default Docker scheduling algorithm. Experiments show that the proposed approach can increase the total value obtained from a workload up to three times depending on the workload heaviness. It is also demonstrated that the algorithms scale well with the growing number of nodes in a cloud.