CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization
Proceedings of the VLDB Endowment · 01.04.2026 · 19 (8) · 1701-1714
DOI: 10.14778/3811243.3811245 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 15.07.2026. Verfasst von Yuxuan Du und 4 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben.
Abstract (Originalsprache)
Memory-disaggregated key-value (KV) stores suffer from a severe performance bottleneck due to their I/O redundancy issues. A huge amount of redundant I/Os are generated when synchronizing concurrent data accesses, making the limited network between the compute and memory pools of DM a performance bottleneck. We identify the root cause for the redundant I/O lies in the mismatch between the optimistic synchronization of existing memory-disaggregated KV stores and the highly concurrent workloads on DM. In this paper, we propose to boost memory-disaggregated KV stores with pessimistic synchronization. We propose CIDER, a compute-side I/O optimization framework, to verify our idea. CIDER adopts a global write-combining technique to further reduce cross-node redundant I/Os. A contention-aware synchronization scheme is designed to improve the performance of pessimistic synchronization under low contention scenarios. Experimental results show that CIDER effectively improves the throughput of state-of-the-art memory-disaggregated KV stores by up to 6.6X under the YCSB benchmark.
Zitieren
APA
Du, Y., Luo, X., Wang, X., Zhou, Y., & Shen, J. (2026). CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization. Proceedings of the VLDB Endowment, 19(8), 1701-1714. https://doi.org/10.14778/3811243.3811245
Vancouver
Du Y, Luo X, Wang X, Zhou Y, Shen J. CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization. Proceedings of the VLDB Endowment. 2026;19(8):1701-1714. doi:10.14778/3811243.3811245
BibTeX
@article{Du2026,
author = {Du, Yuxuan and Luo, Xuchuan and Wang, Xin and Zhou, Yangfan and Shen, Jiacheng},
title = {CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization},
journal = {Proceedings of the VLDB Endowment},
year = {2026},
volume = {19},
number = {8},
pages = {1701--1714},
doi = {10.14778/3811243.3811245}
}
EUVIMED