On the Interplay Between Throughput, Fairness and Energy Efficiency on Asymmetric Multicore Processors. (27th April 2017)

• Record Type: Journal Article
• Authors: Saez, J C; Pousa, A; Giusti, A E de; Prieto-Matias, M
• Is Part Of: Computer journal. Volume 61:Number 1(2018)
• Page Start: 74
• Page End: 94
• Publication Date: 2017-04-27
• Subjects: asymmetric multicore -- scheduling -- operating systems -- energy efficiency -- fairness; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxx038
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: Asymmetric single-ISA multicore processors (AMPs), which integrate high-performance big cores and low-power small cores, were shown to deliver higher performance per watt than symmetric multicores. Previous work has highlighted that this potential of AMP systems can be realizable by scheduling the various applications in a workload on the most appropriate core type. A number of scheduling schemes have been proposed to accomplish different goals, such as system throughput optimization, enforcing fairness or reducing energy consumption. While the interrelationship between throughput and fairness on AMPs has been comprehensively studied, the impact that optimizing energy efficiency has on the other two aspects is still unclear. To fill this gap, we carry out a comprehensive analytical and experimental study that illustrates the interplay between throughput, fairness and energy efficiency on AMPs. Our analytical study allowed us to define the energy-efficiency factor (EEF) metric, which aids the OS scheduler in identifying which applications are more suitable for running on the various cores to ensure a good balance between performance and energy consumption. We propose two energy-aware OS-level schedulers that leverage the EEF metric; the first one strives to optimize the energy-delay product and the second scheduler can be configured to optimize different metrics on the AMP. To demonstrate the effectiveness of these proposals, we performed an extensive evaluation and comparison with state-of-the-art schemes by using real asymmetric hardware and scheduler implementations in the Linux kernel.