Trends and challenges in operating systems—from parallel computing to cloud computing

摘要

Over many decades, advances in computer system design and processor manufacturing have resulted in an ever-increasing per-chip transistor count, which, in combination with increased clock frequencies, has led to a tremendous increase in single-thread performance in desktop and server CPUs. The trend to higher integration in processor manufacturing will continue for the next couple of years. However, the increased transistor count leads to additional compute cores within a CPU, rather than to an increased single-thread performance. Programming and utilizing these future CPUs impose a number of problems commonly referred to as the multicore challenge. These trends primarily affect server computers, whereas on client systems, a break-even between users' willingness to pay for compute power and today's CPU implementation seems to be reached. In this paper, we argue that the full exploitation of many-core architectures on the server demands better support by the operating system. This relates to the support of new application programming models, the seamless integration of internal and external services, security, as well as on monitoring and (self-adaptive) management of such server environments. Within this paper, we discuss three major trends that will drive the adoption of server operating systems to modern many-core hardware: dynamic parallelism, dynamic partitioning, and dynamic provisioning.