Wu CCui YJi CKuo T.-WXue C.J.TEI-WEI KUO2021-09-022021-09-02202002780070https://www.scopus.com/inward/record.uri?eid=2-s2.0-85096037195&doi=10.1109%2fTCAD.2020.3012804&partnerID=40&md5=a4421c0f2f3027c97c2a6400a7f7eb93https://scholars.lib.ntu.edu.tw/handle/123456789/581457Background segment cleaning in log-structured file system has a significant impact on mobile devices. A low triggering frequency of the cleaning activity cannot reclaim enough free space for subsequent I/O, thus incurring foreground segment cleaning and impacting the user experience. In contrast, a high triggering frequency could generate excessive block migrations (BMs) and impair the storage lifetime. Prior works address this issue either by performance-biased solutions or incurring excessive memory overhead. In this article, a pruned reinforcement learning-based approach, MOBC, is proposed. Through learning the behaviors of I/O workloads and the statuses of logical address space, MOBC adaptively reduces the number of BMs and the number of triggered foreground segment cleanings. In order to integrate MOBC to resource-constraint mobile devices, a structured pruning method is proposed to reduce the time and space cost. The experimental results show that the pruned MOBC can reduce the worst case latency by 32.5%-68.6% at the 99.9th percentile, and improve the storage endurance by 24.3% over existing approaches, with significantly reduced overheads. ? 1982-2012 IEEE.Cleaning; Cost reduction; Reinforcement learning; User experience; Address space; Free spaces; Lifetime improvement; Log structured file systems; Memory overheads; Pruning methods; Resource Constraint; Worst-case latencies; Deep learning[SDGs]SDG8journal article10.1109/TCAD.2020.30128042-s2.0-85096037195