Tardiness bounds for fixed-priority global scheduling without intra-task precedence constraints

Abstract

Fixed-priority multiprocessor schedulers are often preferable to dynamic-priority ones because they entail less overhead, are easier to implement, and enable certain tasks to be favored over others. Under global fixed-priority (G-FP) scheduling, as applied to the standard sporadic task model, response times for low-priority tasks may be unbounded, even if the total task system utilization is low. In this paper, it is shown that this negative result can be circumvented if different jobs of the same task are allowed to execute in parallel. In particular, a response-time bound is presented for task systems that allow intra-task parallelism. This bound merely requires that the total utilization does not exceed the overall processing capacity—individual task utilizations need not be further restricted. This result implies that G-FP is optimal for scheduling soft real-time tasks that require bounded tardiness, if intra-task parallelism is allowed.