Title | Job-queuing and Auto-scaling in Container-based Cloud Environments |
---|
Authors | Abu Oun, O. and Kiss, T. |
---|
Editors | Gesing, S. and Atkinson, M. |
---|
Type | Conference paper |
---|
Abstract | Many applications process large quantities of data that takes significant time and requires big amount of compu- tational resources. Optimising the execution of such applications in a cloud computing environment by keeping costs at minimum but still completing the task by a set deadline has paramount importance. As container-based technologies are becoming more widespread, support for job-queuing and auto-scaling in such environments is becoming important. Current container tech- nologies, such as Docker or Kubernetes provide limited support in this area. This paper presents JQueuer and CAutoScaler, a couple of cloud-independent solutions that offer job-queuing and automated scalability at the level of containers. Applying these solutions leads to more cloud-aware applications providing transparent auto-scaling for end-users and optimising execution time and costs. Business and science gateways will benefit from using an orchestrator combined with JQueuer and CAutoScaler since it will provide the layers needed to auto-scale the containers and to batch/sweep the jobs from a queue depending on a user- defined policy. |
---|
Keywords | cloud computing, container technologies, Docker Swarm, JQueuer, autoscaler, MiCADO |
---|
Year | 2018 |
---|
Conference | 10th International Workshop on Science Gateways, IWSG 2018 |
---|
Publisher | CEUR Workshop Proceedings |
---|
Accepted author manuscript | |
---|
Publisher's version | |
---|
Publication dates |
---|
Published | 07 May 2019 |
---|
ISSN | 1613-0073 |
---|
Funder | European Commission |
---|
Web address (URL) of conference proceedings | http://ceur-ws.org/Vol-2357/ |
---|
Web address (URL) | http://ceur-ws.org/Vol-2357/paper10.pdf |
---|