Efficient Virtual Pre-emption based on Local and External Requests in Cloud Computing

Resource provisioning is one of the main challenges in large-scale resource sharing environments such as federated Grids. In resource sharing environments resource providers serve requests from external users along with their own local users. The problem arises when there is not sufficient resources for local users, who have higher priority than external ones, and need resources urgently. This problem could be solved by pre-empting leases from external users and allocating them to the local ones. However, pre-empting leases entails side-effects in terms of overhead time as well as increasing makespan of external requests. In our proposed work, we model the overhead of the pre-empting vms and calculate the number of leases to be pre-empted by proposing an efficient algorithm that considers various scenarios based on the type of the local and external requests and selects the appropriate request to be pre-empted in a manner that the more local requests are served and also reduces the rejection ratio of highly prioritized Requests. Thereby , providing efficient resource provisioning by providing prioritized queues one for each type of request.