“…This process is brittle and increasingly hard as workloads evolve, data and cluster sizes change, and new workloads are added. Thus, techniques have been proposed in the literature to support specific SLOs such as deadlines [14,33,20,45], fast job response times [10,14,23,39], high resource utilization [2,10,14], scalability [2,41,49], and transparent failure recovery [49].…”