Towards Optimal Scheduling of Multiserver System Components

Until recently, microkernel-based multiserver systems could not match the performance of monolithic designs due to their architectural choices which prefer high reliability over high performance. With the advent of multicore processors, het-erogeneous and over-provisioned architectures, it is possible to employ multiple cores to run individual components of the system, avoid expensive context switching and streamline the system’s operations. Thus, multiserver systems can overcome their performance issues without compromising reliability. However, while resources are becoming abundant, it is impor-tant to use them efficiently and to select and tune the resources carefully for the best performance and energy efficiency de-pending on the current workload. Most of the prior work fo-cused solely on scheduling and placement of the applications. In multiserver systems, the operating system itself needs to be scheduled in time and space as the demand changes. There-fore the system servers must no longer be opaque processes and the scheduler must understand the system’s workload to make good decisions. 1