Straw: A Stress-Aware WL-Based Read Reclaim Technique for High-Density NAND Flash-Based SSDs

2025-01-01

IEEE computer architecture letters

AI Summary

Traditional block-level read reclaiming suffers from low efficiency and frequent invalid writes in high-density NAND flash, due to heterogeneous page-level read disturb across word lines (WLs). To address this, this paper proposes the first WL-granularity stress-aware read reclaiming mechanism. Leveraging device-characterization-driven read disturb modeling, WL-level disturbance counters, lightweight metadata management, and an adaptive triggering algorithm, the approach enables fine-grained tracking of disturbance accumulation and selective reclaiming. By breaking away from coarse-grained block-level paradigms, it significantly improves reclaiming precision and energy efficiency: reducing invalid page writes induced by read reclaiming by 83.6%, incurring negligible storage overhead, effectively lowering write amplification, and thereby extending SSD lifetime.

Technology Category

• Search and Optimization: Distributed Search
• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Data Compression

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Although read disturbance has emerged as a major reliability concern, managing read disturbance in modern NAND flash memory has not been thoroughly investigated yet. From a device characterization study using real modern NAND flash memory, we observe that reading a page incurs heterogeneous reliability impacts on each WL, which makes the existing block-level read reclaim extremely inefficient. We propose a new WL-level read-reclaim technique, called Straw, which keeps track of the accumulated read-disturbance effect on each WL and reclaims only heavily-disturbed WLs. By avoiding unnecessary read-reclaim operations, Straw reduces read-reclaim-induced page writes by 83.6% with negligible storage overhead.

Problem

• NAND Flash
• Read Disturbance
• Solid-State Drive (SSD) Performance

Innovation

• STRAW Technology
• Read Disturb Management
• NAND Flash Storage