Improving Cloud Infrastructure Utilization through Overbooking
2013 (English)In: Proceedings of the 2013 ACM Cloud and Autonomic Computing Conference, 2013Conference paper (Refereed)
Despite the potential given by the combination of multitenancyand virtualization, resource utilization in today’sdata centers is still low. We identify three key characteristicsof cloud services and infrastructure as-a-service managementpractices: burstiness in service workloads, fluctuationsin virtual machine resource usage over time, and virtual machinesbeing limited to pre-defined sizes only. Based on thesecharacteristics, we propose scheduling and admission controlalgorithms that incorporate resource overbooking to improveutilization. A combination of modeling, monitoring, andprediction techniques is used to avoid overpassing the totalinfrastructure capacity. A performance evaluation using amixture of workload traces demonstrates the potential forsignificant improvements in resource utilization while stillavoiding overpassing the total capacity.
Place, publisher, year, edition, pages
, ACM International Conference Proceeding Series
Admission Control, Burstiness, Cloud Computing, Overbooking, Prediction, Profiling, Resource Utilization
IdentifiersURN: urn:nbn:se:umu:diva-79780DOI: 10.1145/2494621.2494627ISBN: 978-1-4503-2172-3OAI: oai:DiVA.org:umu-79780DiVA: diva2:644779
2013 ACM International Conference on Cloud and Autonomic Computing, CAC 2013, 5 August 2013 through 9 August 2013, Miami, FL