EFRC is Adapted to Access-rate Imbalance: A Class of Efficient and Fair Replacement Algorithms for Cache Sharing
ACM Transactions on Storage · 30.12.2026 · 22 (4) · 1-35
DOI: 10.1145/3799981 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Storage, online erschienen am 14.08.2026. Verfasst von Liang Ai und 4 weiteren Autor:innen. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Co-located workloads demand fine-grained management of caching control for enhanced deterministic performance. Traditionally, minimizing cache interference has relied on hardware mechanisms that offer coarse cache resource allocation across cores or the last-level cache. More often than not, existing cache replacement algorithms aim to optimize cache hit efficiency depending on single workload access characteristics. In this article, we propose a series of replacement algorithms for multi-workload shared caches, radically enhancing the deterministic performance of co-located workloads. We devise a class of replacement algorithms for cache sharing, referred to as Efficient and Fair Replacement Cache or EFRC. To strick a balance between performance and complexity, we divide the class of algorithms into Type Iand Type IIaccording to the data access characteristics. The common idea of our EFRC-Iand EFRC-IIalgorithms is to judiciously adjust resources for a diversity of workloads or data characteristics online by triggering various resource allocation policies through a corresponding ghost cache preceptor. Our extensive experiments unveil that the EFRC-Iand EFRC-IIalgorithms exhibit a handful of advantages. Firstly, the algorithms support multiple workloads sharing cache—and are compatible with single workload scenarios. Secondly, the cache-hit performance of our proposed EFRC-Iand EFRC-IIalgorithms is superior to that of the existing ARC, LIRS, CACHEUS, and SIEVE algorithms in multi-workload shared caches. Importantly, our technique enhances the fairness of co-located workloads. In particular, when access rates of co-located workloads are imbalanced, our method demonstrates clear superiority over the baseline and the aforementioned state-of-the-art algorithms.
Zitieren
APA
Ai, L., Chen, P., Yu, G., Deng, Y., & Qin, X. (2026). EFRC is Adapted to Access-rate Imbalance: A Class of Efficient and Fair Replacement Algorithms for Cache Sharing. ACM Transactions on Storage, 22(4), 1-35. https://doi.org/10.1145/3799981
Vancouver
Ai L, Chen P, Yu G, Deng Y, Qin X. EFRC is Adapted to Access-rate Imbalance: A Class of Efficient and Fair Replacement Algorithms for Cache Sharing. ACM Transactions on Storage. 2026;22(4):1-35. doi:10.1145/3799981
BibTeX
@article{Ai2026,
author = {Ai, Liang and Chen, Pengfei and Yu, Guangba and Deng, Yuhui and Qin, Xiao},
title = {EFRC is Adapted to Access-rate Imbalance: A Class of Efficient and Fair Replacement Algorithms for Cache Sharing},
journal = {ACM Transactions on Storage},
year = {2026},
volume = {22},
number = {4},
pages = {1--35},
doi = {10.1145/3799981}
}
EUVIMED