EUVIMEDEUVIMED entdecken
Crossref

Epiphron: Resource-Efficient Distributed Key-Value Storage

Ruidong Zhu, Zili Zhang, Bingyang Wu, Xin Yao, Renhai Chen, Gong Zhang, Xuanzhe Liu, Xin Jin

IEEE Transactions on Knowledge and Data Engineering · 2026-05 · 38 (5) · 2779-2792

DOI: 10.1109/tkde.2026.3669983 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-05. Verfasst von Ruidong Zhu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Scientific Research Innovation Capability Support Project for Young Faculty.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In-memory key-value storage necessitates a substantial quantity of computation and storage resources for both performance and scalability, thereby diminishing the resources available for user applications. The emergence of programmable network hardware, including SmartNICs and programmable switches, provides the opportunity to offload operations from server CPUs. We present Epiphron, a novel distributed in-memory key-value store architecture that co-designs with off-path SmartNICs and programmable switches. Facing the limited performance of off-path SmartNICs, Epiphron successfully achieves high resource efficiency while keeping load balancing and fault tolerance by $(i)$ ( i ) hybridizing erasure coding with replication in storage management, $(ii)$ ( i i ) accelerating read operations with a new data plane design (conflict detection and RDMA-compatible forwarding) on programmable switches, $(iii)$ ( i i i ) employing a network protocol extended from one-sided RDMA. We evaluate Epiphron on Barefoot Tofino switches, NVIDIA BlueField-2 SmartNICs, and commodity servers. The experimental results demonstrate that compared to existing solutions, Epiphron improves throughput by up to 2.2× and consumes 47% less memory while completely bypassing server CPUs.

Förderung

  • National Natural Science Foundation of China
  • Scientific Research Innovation Capability Support Project for Young Faculty

Zitieren

APA

Zhu, R., Zhang, Z., Wu, B., Yao, X., Chen, R., Zhang, G., Liu, X., & Jin, X. (2026). Epiphron: Resource-Efficient Distributed Key-Value Storage. IEEE Transactions on Knowledge and Data Engineering, 38(5), 2779-2792. https://doi.org/10.1109/tkde.2026.3669983

Vancouver

Zhu R, Zhang Z, Wu B, Yao X, Chen R, Zhang G, et al. Epiphron: Resource-Efficient Distributed Key-Value Storage. IEEE Transactions on Knowledge and Data Engineering. 2026;38(5):2779-2792. doi:10.1109/tkde.2026.3669983

BibTeX
@article{Zhu2026,
  author = {Zhu, Ruidong and Zhang, Zili and Wu, Bingyang and Yao, Xin and Chen, Renhai and Zhang, Gong and Liu, Xuanzhe and Jin, Xin},
  title = {Epiphron: Resource-Efficient Distributed Key-Value Storage},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {5},
  pages = {2779--2792},
  doi = {10.1109/tkde.2026.3669983}
}
Kostenlos starten →