The Research About Resources And Data Management In Private Cloud Architecture

With the accelerating pace of global information technology and compute sciencetechnology research, Cloud compute become a new way of delivering computingresources and storage capacity as a service to heterogeneous community ofend-recipients. Cloud computing is not a new technology. Computing servicesranging from data storage and processing to software, are now available instantly,such as email handling and search engine. This dissertation research works includekey technology of Cloud computing in resources and data management.End users access cloud based applications through a web browser or a lightweight desktop or mobile app while the business software and data are stored onservers at a remote server. Proponents claim that cloud computing allows enterprisesto get their applications up and running faster, with improved manageability and lessmaintenance, and enables enterprises to more rapidly adjust resources to meetfluctuating and unpredictable business demand.Cloud computing relies on sharing ofresources to achieve coherence and economies of scale similar to a utility (like theelectricity grid) over a network (typically the Internet). Cloud computing will haveinfluence on many domains, just like Hygiene, Medical Care, Education, andInformation Technology system.At the foundation of cloud computing is the broader concept of convergedinfrastructure and shared services. How to manage compute resources in diversedistributed network environment to access a large number of data is one researchspot in this dissertation. The primarily reserarch works include the followingrespects.Design to provision and manage large networks of virtual machines, create aredundant and scalable cloud computing platform. It gives the method, controlpanels, and APIs required to orchestrate a cloud, including running instances,managing networks, and controlling access through users and projects.Design a PB level object storage system, which is a storage system for a morepermanent type of static data,both structured and un-structured. This storage systemusing clusters of standardized servers to store petabytes data, but it is simple and large-scaled. The design of the storage system base on many other DFS, like GFS,Ceph,and Dynamo. The system has no central point of failure, so it’s extremely faulttolerant, and the data and related metadata are distributed throughout the system, sothere are no central scalability constraints.