CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913001604382720 |
|---|---|
| author | Du, Yuxuan Luo, Xuchuan Wang, Xin Zhou, Yangfan Shen, Jiacheng |
| author_facet | Du, Yuxuan Luo, Xuchuan Wang, Xin Zhou, Yangfan Shen, Jiacheng |
| contents | 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 $6.6\times$ under the YCSB benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03007 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization Du, Yuxuan Luo, Xuchuan Wang, Xin Zhou, Yangfan Shen, Jiacheng Distributed, Parallel, and Cluster Computing Databases 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 $6.6\times$ under the YCSB benchmark. |
| title | CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization |
| topic | Distributed, Parallel, and Cluster Computing Databases |
| url | https://arxiv.org/abs/2604.03007 |