VM Resource Allocation Isolation Technology in Cloud System

CLOUD computing has emerged as a compelling paradigm for the deployment of ease-of-use virtual environment on the Internet. One typical feature of clouds is its pool of easily accessible virtualized resources (such as hardware, platform or services) that can be dynamically reconfigured to adjust to a variable load (scale). Cloud systems usually do not provision physical hosts directly to users. Successful platforms or cloud management tools leveraging VM resource isolation technology, but leverage virtual resources isolated by VM technology. The VM-based divisible resource allocation could be very flexible. It is inviable to directly solve the necessary and sufficient condition to find the optimal solution. Karush-Kuhn-Tucker (KKT) conditions and contribution is devising a novel approach. A deadline-driven resource allocation problem based on the cloud environment facilitated with VM resource isolation technology. The analyzing the upper bound of task execution length based on the possibly inaccurate workload prediction, we further propose an error-tolerant method to guarantee task’s completion within its deadline. The validate its effectiveness over a real VM-facilitated cluster environment under different levels of competition. The elastic resource usage model, we aim to design a resource allocation algorithm with high prediction error tolerance ability, also minimizing users’ payments subject to their expected deadlines. In this paper, we propose a novel resource allocation algorithm for cloud system that supports VM-multiplexing technology, aiming to minimize user’s payment on his/her task and also endeavor to guarantee its execution deadline meanwhile. We can prove that the output of our algorithm is optimal based on the KKT condition, which means any other solutions would definitely cause larger payment cost.