Impact of job deadlines on the QoS performance of cloud data centers

Job scheduling affects the performance of a cloud data center in terms of essential Quality-of-Service (QoS) metrics such as the blocking probability and the system´s response time. This paper´s first contribution lies in the proposal of a novel job Deadline-Aware Scheduling Scheme (DASS) with the objective of improving a data center´s QoS in term of the above-mentioned metrics. An analytical queueing model is developed for the purpose of capturing the data center´s behavioral dynamics and evaluating its performance when operating under DASS. The model´s results and their accuracy are verified through extensive simulations. Furthermore, the performance of the data center achieved under DASS is compared to its counterpart achieved under the more widely adopted First-In-First-Out (FIFO) scheme. Results indicate that DASS outperforms FIFO by 11% to 58% in terms of the blocking probability and by 82% to 89% in terms of the system´s response time.