SS-LRU: A Smart Segmented LRU Caching for Storage System
TimeTuesday, July 12th4:30pm - 4:50pm PDT
Location3004, Level 3
Event Type
Research Manuscript
Embedded Memory, Storage and Networking
Embedded Systems
DescriptionMany caching policies use machine learning to predict the data reuse, ignoring the cache cost due to misprediction, especially for large-size objects. In this paper, we propose a smart segmented LRU (SS-LRU) replacement policy, which adopts a size-aware classifier designed for cache scenarios considering the cache cost caused by misclassification. Besides, we enhance the promotion rules of segmented LRU (SLRU) based our classifier and implement an adaptive SLRU caching. We conducted extensive experiments under the real-world workloads to demonstrate the superiority of our approach: a higher hit ratio and lower access latency compared to the state-of-the-art cache replacement algorithms.