A self-tuning job scheduler family with dynamic policy switching

The performance of job scheduling policies strongly depends on the properties of the incoming jobs. If the job characteristics often change, the scheduling policy should follow these changes. For this purpose the dynP job scheduler family has been developed. The idea is to dynamically switch the scheduling policy during runtime. In a basic version the policy switching is controlled by two parameters. The basic concept of the self-tuning dynP scheduler is to compute virtual schedules for each policy in every scheduling step. That policy is chosen which generates the 'best' schedule. The performance of the self-tuning dynP scheduler no longer depends on a adequate setting of the input parameters. We use a simulative approach to evaluate the performance of the self-timing dynP scheduler and compare it with previous results. To drive the simulations we use synthetic job sets that axe based on trace information from four computing centers (CTC, KTH, PC2, SDSC) with obviously different characteristics.