Improving Priority Enforcement via Non-Work-Conserving Scheduling

Current operating system schedulers are not fully aware of multi-core and multi-threaded architectures, and as a result, schedule threads in a way that may cause contention for critical resources such as the last level in the cache memory hierarchy or the memory access bandwidth. This contention has a significant impact on the system productivity and the quality of service that each individual thread gets from the platform, which can widely vary depending on the behavior of its simultaneous co-runners.In this paper we describe the design and implementation of a non-work-conserving framework to schedule threads that tries to improve priority enforcement, based on on-line statistics collected through hardware performance counters. We have implemented our scheme in Linux running on both multicore and SMT processors. For synthetic  workloads based on the latest SPEC CPU2006 benchmarks, our framework speeds up high-priority threads by up to 50%, while keeping or even slightly improving the overall system throughput.