Reinforcement Learning-Assisted Management for Convertible SSDs

Convertible SSDs, which allow flash cells to convert between different types of flash cells (e.g., SLC/MLC/TLC/QLC), are designed for achieving both high performance and high density. However, previous designs with two types of flash cells encounter a performance cliff degradation once the flash cel...

Full description

Saved in:
Bibliographic Details
Published in:2023 60th ACM/IEEE Design Automation Conference (DAC) pp. 1 - 6
Main Authors: Wei, Qian, Li, Yi, Jia, Zhiping, Zhao, Mengying, Shen, Zhaoyan, Li, Bingzhe
Format: Conference Proceeding
Language:English
Published: IEEE 09.07.2023
Subjects:
Convertible SSD
Degradation
Design automation
Flash memory
Performance evaluation
Q-learning
Real-time systems
Reinforcement learning
Resource management
Throughput
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convertible SSDs, which allow flash cells to convert between different types of flash cells (e.g., SLC/MLC/TLC/QLC), are designed for achieving both high performance and high density. However, previous designs with two types of flash cells encounter a performance cliff degradation once the flash cells of single bit mode are consumed. In this work, we propose a novel level-based convertible SSD (e.g., including SLC-MLC-QLC), named RL-cSSD, that adopts an intermediate layer (e.g., MLC) as a performance cushion. A reinforcement learning-assisted device management scheme is designed to coordinate the data allocation, garbage collection and flash conversion processes considering both the SSD internal status and workload patterns. We evaluated RL-cSSD with various real-world workloads based on simulation. The experimental results show that the proposed RL-cSSD provides 72.98% higher performance on average compared with state-of-the-art schemes.
DOI:10.1109/DAC56929.2023.10247929