Modern hardware and economic trends are driving the adoption of distributed storage engines that expose a transparent, shared-cache abstraction: any node can access both the cluster’s aggregate DRAM and its NVMe storage over a fast (RDMA) network. To sustain performance under changing workloads, these systems must continuously evict and re-cache pages at very high rates. However, most designs still rely on node-local eviction algorithms such as LRU, which waste aggregate DRAM by retaining redundant page copies. We propose ScaleEvict, an altruistic eviction strategy implemented in the state-of-the-art ScaleStore engine. ScaleEvict efficiently coordinates eviction decisions across nodes to reduce redundant replication and prioritize globally valuable pages. ScaleEvict matches ScaleStore’s throughput using only two-thirds of the DRAM. Alternatively, at equal DRAM capacity, ScaleEvict improves throughput by up to 2 × while reducing 99th percentile latency by up to 3 ×.

Virtual Reality (VR) bicycle simulations aim to recreate the feeling of riding a bicycle and are commonly used in many application areas. However, current solutions still create mismatches between the visuals and physical movement, which causes VR sickness and diminishes the cycling experience. To reduce VR sickness in bicycle simulators, we conducted two controlled lab experiments addressing two main causes of VR sickness: (1) steering methods and (2) cycling trajectory. In the first experiment (N = 18) we compared handlebar, HMD, and upper-body steering methods. In the second experiment (N = 24) we explored three types of movement in VR (1D, 2D, and 3D trajectories) and three countermeasures (airflow, vibration, and dynamic Field-of-View) to reduce VR sickness. We found that handlebar steering leads to the lowest VR sickness without decreasing cycling performance and airflow suggests to be the most promising method to reduce VR sickness for all three types of trajectories.