Power-Aware Network Swapping for Wireless Palmtop PCs

Virtual memory is considered to be an unlimited resource in desktop or notebook computers with high storage capabilities. However, in wireless mobile devices, like palmtops and personal digital assistants (PDAs), storage memory is limited or absent due to weight, size, and power constraints, so that swapping over remote memory devices can be considered as a viable alternative. However, power-hungry wireless network interface cards (WNICs) may limit the battery lifetime and application performance if not efficiently exploited. In this paper, we study performance and energy of network swapping in comparison with swapping on local microdrives and flash memories. We report the results of extensive experiments conducted on different WNICs and local swapping devices, using both synthetic and natural benchmarks. Our study points out that remote swapping over power-manageable WNICs can be more efficient than local swapping, especially in bursty workload conditions. Such conditions can be forced where possible by reshaping swapping requests to increase energy efficiency and performance. The contribution of the paper is threefold. First, we characterize all swap devices in terms of time and energy inherently required to swap a single page. Second, we test the effectiveness of the dynamic power management (DPM) support made available by each device. Third, we show in a case study that dummy data accesses can be preemptively inserted in the source code to reshape page requests in order to improve the effectiveness of DPM. Data traffic reshaping is a well-known technique used to increase energy efficiency of storage devices. Here we study its relationship with dynamic power management techniques of both storage devices and wireless network interfaces. Experimental results show that WNICs are less efficient than local devices both in terms of energy and time per page. However, the DPM support provided by WNICs is much more efficient than that of local micro drives, making network swapping even less expensive than local swapping for real-world applications with nonuniform page requests.