Skip to content
Open access

Reducing Write Operations in Flash Memory Using a Modified CFLRU Page Replacement Algorithm

Aug 2026 · Journal of Physical and Life Sciences · 0 citations · 13 references

TL;DR

An enhancement to the Clean First LRU (CFLRU) algorithm, termed Dirty Hot Clean Hot CFLRU (DCH-CFLRU), which provides both clean and dirty pages with a second chance, and exhibits better overall flash memory performance and extending its lifespan.

Abstract

Modern computing system heavily depends on the flash-based memory system. Effective cache management is fundamental to improving performance and extending lifespan of flash memory. Traditional page-replacement algorithms, such as LRU, were originally designed for magnetic disks and do not fully deal with the unique characteristics of flash memory, including asymmetric read and write speeds and limited erase operations. This article introduces an enhancement to the Clean First LRU (CFLRU) algorithm, termed Dirty Hot Clean Hot CFLRU (DCH-CFLRU), which provides both clean and dirty pages with a second chance. The proposed solution aims to reduce write counts while upholding a stable hit ratio. Experimental outcomes show that DCH-CFLRU reduces write operation by up to 14% compared to CFLRU through multiple datasets specially in write most cases. The modified algorithm exhibits better overall flash memory performance and extending its lifespan.

Read PDF

Similar papers

Open access Sep 2026

Lightweight Cache Buffer Management and Data Allocation Strategy for Enhancing Read/Write Latency in SSDs

A Lightweight Cache Buffer Management (LCBM) strategy that avoids precise frequency tracking altogether and reduces the average read latency and the write response time, while eliminating the metadata overhead of counter- and LRU-based designs is introduced.

Li-Lung Hsieh, Qi-Cheng Wu, Yu-Pei Liang · 0 citations
Conference Aug 2026

Paging-Resilient Prefetching in Flash-Based CXL SSDs

CXL SSDs extend system memory using NAND flash, providing a scalable solution to the capacity and bandwidth limits of memory-intensive, multi-tenant cloud services. Since CXL SSDs are directly addressable by the CPU, SSD-internal prefetching is crucial for hiding flash-grade latency from the host. However, host-side pa...

Chung-Min Yu, Chih-Kang Yeh, Ying-Shuo Lin et al. · 0 citations
Aug 2026

Optimizing Massive Directory Traversal on Portable Flash Storage Via Continuity-Aware Dynamic Read-Ahead

Portable flash devices, such as TF cards, widely adopt the exFAT file system due to its cross-platform compatibility and support for large-capacity storage. However, directory entries in exFAT exhibit a distributed storage characteristic. When traversing files within massive small directories, a single read request for...

Haodong Xia, Zhi-Wei Li, Wen-Yu Zheng et al. · 0 citations
Open access 2026

Compression for Tiering: Enabling High-Tier Flash Storage for Hot Data via Cold Data Compression

Advances in flash memory technology have increased the number of bits stored per cell, significantly reducing the cost of solid-state drives (SSDs). As a result, SSDs using high-density flash have become common, though they suffer from lower performance and endurance than low-density flash. Modern SSDs exploit the abil...

Cha-Nu Yu, Jongseok Kim, Euiseong Seo · 0 citations
Aug 2026

RARO: Reliability-Aware Read Optimization for Hybrid Flash Storage

Hybrid flash storage combines large-capacity highdensity flash memory with high-performance low-density flash memory, providing excellent cost-effectiveness. Existing data placement strategies for hybrid flash storage typically employ hotness-based data migration relying on a twotier architecture. This approach not onl...

Han Yan, Dingcui Yu, Yanyun Wang et al. · 0 citations
Book Open access Sep 2026

4Z-SSD: A Semantic-Aware Four-Zone SSD Architecture for Balancing Write Amplification and Flash-Level Parallelism

Modern SSDs face a fundamental trade-off between reducing write amplification and maximizing flash-level parallelism. Conventional FTL schemes improve resource utilization through aggressive data distribution, but incur higher garbage collection overhead by intermixing data with different update behaviors. In contrast,...

Dongjun Lee, Han Jang, Youngbin Jin et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.