Data centre energy efficiency optimisation in high-speed packet I/O frameworks

To meet the demands for faster network packet processing requirements in data centres, packet I/O accelerator solutions have emerged which are dedicated to enabling faster packet forwarding capabilities. Often, such I/O frameworks are implemented in software that is hosted on a Linux operating system and for many of the solutions the software is run in the system's userspace, thus bypassing the operating system's kernel to facilitate a streamlined packet throughput rate. However, operating outside of the kernel loses the real-time interrupt facility, so many of the I/O accelerator schemes rely on a very high-speed polling solution to react to receive packet traffic arrivals; the continuous fast polling rate results in the CPU running hot and wasting energy. An experimental approach to reduce such energy inefficiencies is introduced based on an adaptive polling mechanism (APM). The investigation results show potential energy CPU savings ranging between 9% and 76%.