Phoenix CloudConsolidating Different Computing Loads on Shared Cluster System for Large Organization.PDF

Phoenix Cloud: Consolidating Different Computing Loads on Shared Cluster System for Large Organization Jianfeng Zhan, Lei Wang, Bibo Tu, Yong Li, Peng Wang, Wei Zhou, Dan Meng Institute of Computing Technology Chinese Academy of Sciences, Beijing 100190, China jfzhan@ ABSTRACT simple storage service (S3) to end users. What is the link Different departments of large organization often maintain between the service provided by Amazon and the dedicated cluster systems for different computing loads. In requirement of our anonymous client? In our opinion, this paper, we have designed and implemented a cloud driven by the cost, the cloud computing is a new wave of management system software-Phoenix Cloud to consolidate reconstructing and consolidating data center. Traditional heterogeneous computing loads on shared cluster system. cluster system software is self-containing [2], inadequate Furthermore, we have proposed a cooperative resource for adapting to this change. EC2 and S3 are big efforts to provision and management policy for large organization provide virtualized hosting environments for end users, but and its affiliated departments to share the aggregated it can not provide the customized system stack software to cluster system. The experiments show: comparing with the consolidate heterogeneous loads on the shared cluster case that each department maintains its dedicated cluster system f