State-Dependent Deadline Scheduling

This paper presents a new workload model, called the state-dependent deadline model, for applications whose high-level timing requirements may change with time. The problem is how to choose target deadlines for jobs from their time-varying deadlines so that the system can meet its requirements with a high probability. In the clairvoyant case, the deadline of every job is given by a known function of time for all times after the job is released. There is an optimal deadline determination algorithm. When the future values of job deadlines are unknown, it is not possible to make optimal choices of job deadlines. Several heuristics can be used to determine deadlines in this realistic case. Simulation results show that these heuristics allow the system to achieve good processor utilization and high probability of meeting its time-varying requirements.