The Community for Technology Leaders
Green Image
Issue No. 01 - January-June (2013 vol. 1)
ISSN: 2168-7161
pp: 1
Mukil Kesavan , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
Irfan Ahmad , CloudPhysics, Inc., Mountain View, CA, USA
Orran Krieger , Dept. of Comput. Sci., Boston Univ., Boston, MA, USA
Ravi Soundararajan , VMware, Inc., Palo Alto, CA, USA
Ada Gavrilovska , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
Karsten Schwan , Coll. of Comput., Georgia Inst. of Technol., Atlanta, GA, USA
We present CCM (Cloud Capacity Manager) - a prototype system and its methods for dynamically multiplexing the compute capacity of virtualized datacenters at scales of thousands of machines, for diverse workloads with variable demands. Extending prior studies primarily concerned with accurate capacity allocation and ensuring acceptable application performance, CCM also sheds light on the tradeoffs due to two unavoidable issues in large scale commodity datacenters: (i) maintaining low operational overhead given variable cost of performing management operations necessary to allocate resources, and (ii) coping with the increased incidences of these operations' failures. CCM is implemented in an industry-strength cloud infrastructure built on top of the VMware vSphere virtualization platform and is currently deployed in a 700 physical host datacenter. Its experimental evaluation uses production workload traces and a suite of representative cloud applications to generate dynamic scenarios. Results indicate that the pragmatic cloud-wide nature of CCM provides up to 25% more resources for workloads and improves datacenter utilization by up to 20%, compared to the common alternative approach of multiplexing capacity within multiple independent smaller datacenter partitions.
Resource management, Distributed processing, Fault tolerance, Hierarchical systems, Virtualization, Data processing, Cloud computing

M. Kesavan, I. Ahmad, O. Krieger, R. Soundararajan, A. Gavrilovska and K. Schwan, "Practical Compute Capacity Management for Virtualized Datacenters," in IEEE Transactions on Cloud Computing, vol. 1, no. 1, pp. 1, 2013.
300 ms
(Ver 3.3 (11022016))