An experimental evaluation of datacenter workloads on low-power embedded micro servers

This paper presents a comprehensive evaluation of an ultra- low power cluster, built upon the Intel Edison based micro servers. The improved performance and high energy effi- ciency of micro servers have driven both academia and in- dustry to explore the possibility of replacing conventional brawny servers with a larger swarm of embedded micro ser- vers. Existing attempts mostly focus on mobile-class mi- cro servers, whose capacities are similar to mobile phones. We, on the other hand, target on sensor-class micro servers, which are originally intended for uses in wearable technolo- gies, sensor networks, and Internet-of-Things. Although sensor-class micro servers have much less capacity, they are touted for minimal power consumption (< 1 Watt), which opens new possibilities of achieving higher energy efficiency in datacenter workloads. Our systematic evaluation of the Edison cluster and comparisons to conventional brawny clus- ters involve careful workload choosing and laborious param- eter tuning, which ensures maximum server utilization and thus fair comparisons. Results show that the Edison clus- ter achieves up to 3:5× improvement on work-done-per-joule for web service applications and data-intensive MapReduce jobs. In terms of scalability, the Edison cluster scales lin- early on the throughput of web service workloads, and also shows satisfactory scalability for MapReduce workloads de- spite coordination overhead.