Nova-LSM: A Distributed, Component-based LSM-tree Key-value Store
Haoyu Huang, Shahram Ghandeharizadeh
摘要
The cloud infrastructure motivates disaggregation of monolithic data stores into components that are assembled together based on an application's workload. This study investigates disaggregation of an LSM-tree key-value store into components that communicate using RDMA. These components separate storage from processing, enabling processing components to share storage bandwidth and space. The processing components scatter blocks of a file (SSTable) across an arbitrary number of storage components and balance load across them using power-of-d. They construct ranges dynamically at runtime to parallelize compaction and enhance performance. Each component has configuration knobs that control its scalability. The resulting component-based system, Nova-LSM, is elastic. It outperforms its monolithic counterparts, both LevelDB and RocksDB, by several orders of magnitude with workloads that exhibit a skewed pattern of access to data.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper13
- CaaS-LSM: Compaction-as-a-Service for LSM-based Key-Value Stores in Storage Disaggregated InfrastructureQiaolin Yu, Chang Guo, Jay Zhuang, Viraj Thakkar 等SIGMOD 2024 · 被引用 18 次
- Cosine: A Cloud-Cost Optimized Self-Designing Key-Value Storage EngineSubarna Chatterjee, Meena Jagadeesan, Wilson Qin, Stratos IdreosVLDB 2022 · 被引用 17 次
- Aster: Enhancing LSM-structures for Scalable Graph DatabaseDingheng Mo, Junfeng Liu, Fan Wang, Siqiang LuoSIGMOD 2025 · 被引用 10 次
- Ethane: An Asymmetric File System for Disaggregated Persistent MemoryMiao Cai, Junru Shen, Baoliu YeUSENIX ATC 2024 · 被引用 9 次
- p2KVS: a portable 2-dimensional parallelizing framework to improve scalability of key-value stores on SSDsZiyi Lu, Qiang Cao, Hong Jiang, Shucheng Wang 等EuroSys 2022 · 被引用 9 次
它引用的顶会 Paper8
- MatrixKV: Reducing Write Stalls and Write Amplification in LSM-tree Based KV Stores with Matrix Container in NVMTing Yao, Yiwen Zhang, Jiguang Wan, Qiu Cui 等USENIX ATC 2020 · 被引用 186 次
- From WiscKey to Bourbon: A Learned Index for Log-Structured Merge TreesYifan Dai, Yien Xu, Aishwarya Ganesan, Ramnatthan Alagappan 等OSDI 2020 · 被引用 138 次
- AC-Key: Adaptive Caching for LSM-based Key-Value StoresFenggang Wu, Ming-Hong Yang, Baoquan Zhang, David H. C. DuUSENIX ATC 2020 · 被引用 81 次
- Hailstorm: Disaggregated Compute and Storage for Distributed LSM-based DatabasesLaurent Bindschaedler, Ashvin Goel, Willy ZwaenepoelASPLOS 2020 · 被引用 51 次
- Low-Latency Communication for Fast DBMS Using RDMA and Shared MemoryPhilipp Fent, Alexander van Renen, Andreas Kipf, Viktor Leis 等ICDE 2020 · 被引用 44 次
相关 Paper
- dLSM: An LSM-Based Index for Memory DisaggregationRuihong Wang, Jianguo Wang, Prishita Kadam, M. Tamer Özsu 等ICDE 2023 · 被引用 27 次
- O3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer OffloadingQi Lin, Gangqi Huang, Te Guo, Chang Guo 等SIGMOD 2026 · 被引用 2 次
- Scalable Distributed Inverted List Indexes in Disaggregated MemoryManuel Widmoser, Daniel Kocher, Nikolaus AugstenSIGMOD 2024 · 被引用 5 次
- ROLEX: A Scalable RDMA-oriented Learned Key-Value Store for Disaggregated Memory SystemsPengfei Li, Yu Hua, Pengfei Zuo, Zhangyu Chen 等FAST 2023 · 被引用 90 次
- Outback: Fast and Communication-efficient Index for Key-Value Store on Disaggregated MemoryYi Liu, Minghao Xie, Shouqian Shi, Yuanchao Xu 等VLDB 2025 · 被引用 5 次
