Decentralized cloud datacenter reconsolidation through emergent and topology-aware behavior
2016 (English)In: Future generations computer systems, ISSN 0167-739X, E-ISSN 1872-7115, Vol. 56, 51-63 p.Article in journal (Refereed) Published
Consolidation of multiple applications on a single Physical Machine (PM) within acloud data center can increase utilization, minimize energy consumption, and reduceoperational costs. However, these benefits comes at the cost of increasing the complex-ity of the scheduling problem.In this paper, we present a topology-aware resource management framework. Aspart of this framework, we introduce a Reconsolidating PlaceMent scheduler (RPM)that provides and maintains durable allocations with low maintenance costs for datacenters with dynamic workloads. We focus on workloads featuring both short-livedbatch jobs and latency-sensitive services such as interactive web applications. Thescheduler assigns resources to Virtual Machines (VMs) and maintains packing effi-ciency while taking into account migration costs, topological constraints, and the riskof resource contention, as well as the variability of the background load and its com-plementarity to the new VM.We evaluate the model by simulating a data center with over 65000 PMs, structuredas a three-level multi-rooted tree topology. We investigate trade-offs between factorsthat affect the durability and operational cost of maintaining a near-optimal packing.The results show that the proposed scheduler can scale to the number of PMs in thesimulation and maintain efficient utilization with low migration costs.
Place, publisher, year, edition, pages
Elsevier, 2016. Vol. 56, 51-63 p.
Cloud computing, Peer to Peer, VM consolidation, Resource management
Computer and Information Science
Research subject Computer Systems
IdentifiersURN: urn:nbn:se:umu:diva-109131DOI: 10.1016/j.future.2015.09.023ISI: 000368652500004OAI: oai:DiVA.org:umu-109131DiVA: diva2:855198