On the Balance between Performance and Fairness in Multi-Tenant Cache Environments
Abstract
Multi-tenant web caches are susceptible to performance interference, where one tenant’s activity can negatively impact others. Traditional fairness policies, like FairShare, aim to mitigate this by providing fair resource allocation. However, their suitability for caching environments is not well established. In this work, we investigate the performance of FairShare using production traces from a large-scale e-commerce platform. Through simulation, we evaluate its effectiveness in balancing fairness and overall system performance. Our results reveal that while FairShare eliminates interference, it significantly degrades the cache Hit Ratio, demonstrating that classical fairness policies are not directly applicable to caching scenarios. This highlights the need for cache-aware fairness mechanisms that consider the specific characteristics of web caches.
Keywords:
Cache, Performance, Fairness, Multi-tenant
References
BERTSEKAS, D.; GALLAGER, R. Data Networks. second. [S.l.]: Prentice Hall, 1996.
BOUDEC, J.-Y. L. Rate adaptation, congestion control and fairness: A tutorial. 01 2002.
HAHNE, E. L. Round-robin scheduling for max-min fairness in data networks. IEEE J. Sel. Areas Commun., v. 9, n. 7, p. 1024–1039, 1991.
LIRA, A. et al. No clash on cache: Observations from a multi-tenant ecommerce platform. In: Proceedings of the 2024 ACM/SPEC International Conference on Performance Engineering. [S.l.: s.n.], 2024 A.
LIRA, A. et al. Desafios na gerência de cache web multi-locatários. In: Anais Estendidos do XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos. [S.l.: s.n.], 2024 B. p. 283–288. ISSN 2177-9384.
MATTSON, R. et al. Evaluation techniques for storage hierarchies. IBM Systems Journal, v. 9, n. 2, p. 78–117, 1970.
RAWLS, J. A Theory of Justice. Cambridge, Mass: The Belknap press of Harvard University Press, 1971. Eleventh printing, 1981.
XIANG, X. et al. HOTL: a higher order theory of locality. In: ASPLOS 2013. [S.l.]: ACM, 2013. p. 343–356.
BOUDEC, J.-Y. L. Rate adaptation, congestion control and fairness: A tutorial. 01 2002.
HAHNE, E. L. Round-robin scheduling for max-min fairness in data networks. IEEE J. Sel. Areas Commun., v. 9, n. 7, p. 1024–1039, 1991.
LIRA, A. et al. No clash on cache: Observations from a multi-tenant ecommerce platform. In: Proceedings of the 2024 ACM/SPEC International Conference on Performance Engineering. [S.l.: s.n.], 2024 A.
LIRA, A. et al. Desafios na gerência de cache web multi-locatários. In: Anais Estendidos do XLII Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos. [S.l.: s.n.], 2024 B. p. 283–288. ISSN 2177-9384.
MATTSON, R. et al. Evaluation techniques for storage hierarchies. IBM Systems Journal, v. 9, n. 2, p. 78–117, 1970.
RAWLS, J. A Theory of Justice. Cambridge, Mass: The Belknap press of Harvard University Press, 1971. Eleventh printing, 1981.
XIANG, X. et al. HOTL: a higher order theory of locality. In: ASPLOS 2013. [S.l.]: ACM, 2013. p. 343–356.
Published
2025-05-19
How to Cite
RAMALHO, João; NERY, Ana; LIRA, Anna; PEREIRA, Thiago Emmanuel; BRASILEIRO, Francisco Vilar; MENDES, Mariana.
On the Balance between Performance and Fairness in Multi-Tenant Cache Environments. In: INNOVATION AND INDUSTRY INTERACTION TRACK - BRAZILIAN SYMPOSIUM ON COMPUTER NETWORKS AND DISTRIBUTED SYSTEMS (SBRC), 43. , 2025, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 346-351.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc_estendido.2025.5781.
