LinnOS: Predictability on Unpredictable Flash Storage with a Light Neural Network

This paper presents LinnOS, an operating system that leverages a light neural network for inferring SSD performance at a very fine-per-IO-granularity and helps parallel storage applications achieve performance predictability. Lin-nOS supports black-box devices and real production traces without requiring any extra input from users, while outperforming industrial mechanisms and other approaches. Our evaluation shows that, compared to hedging and heuristicbased methods, LinnOS improves the average I/O latencies by 9.6-79.6% with 87-97% inference accuracy and 4-6µs inference overhead for each I/O, demonstrating that it is possible to incorporate machine learning inside operating systems for real-time decision-making.