CaaS-LSM: Compaction-as-a-Service for LSM-based Key-Value Stores in Storage Disaggregated Infrastructure

Summary: CaaS-LSM turns LSM compaction into a decoupled, stateless service for disaggregated storage, removing tight KVS/compactor dependence and coordination overhead. A control plane handles adaptive scheduling, resource balancing, and transient-error recovery, yielding large throughput and tail-latency gains over prior offloaded-compaction designs. (summarized by gpt-5.4-mini on May 24 2026)

Paper ID: 6951
Venue: SIGMOD
Year: 2024
Pagerank: 5.5663461e-05
Overall Rank: 7,693 | 47.22%
DOI: 10.1145/3654927

Incoming Non-self Citations Over Time

Authors

1. Qiaolin Yu (Arizona State University; Cornell University)
2. Chang Guo (Arizona State University)
3. Jay Zhuang (Independent)
4. Viraj Thakkar (Arizona State University)
5. Jianguo Wang (Purdue University)
6. Zhichao Cao (Arizona State University)

BibTeX Citation

@inproceedings{yu_sigmod24,
        title = {{CaaS-LSM: Compaction-as-a-Service for LSM-based Key-Value Stores in Storage Disaggregated Infrastructure}},
        author = {Yu, Qiaolin and Guo, Chang and Zhuang, Jay and Thakkar, Viraj and Wang, Jianguo and Cao, Zhichao},
        series = {{SIGMOD} '24},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3654927},
        url = {https://dl.acm.org/doi/10.1145/3654927},
        year = {2024}
}

Incoming Citations (Sorted by Pagerank)

Showing 8 of 8 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,341	Understanding the Performance Implications of the Design Principles in Storage-Disaggregated Databases	2024	SIGMOD	5.6390976e-05
8,781	Fast Vector Search in PostgreSQL: A Decoupled Approach	2026	CIDR	5.374155e-05
9,963	SHIELD: Encrypting Persistent Data of LSM-KVS from Monolithic to Disaggregated Storage	2025	SIGMOD	5.18753e-05
10,073	DFlush: DPU-Offloaded Flush for Disaggregated LSM-based Key-Value Stores	2025	SIGMOD	5.1624218e-05
10,274	O3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer Offloading	2026	SIGMOD	5.093636e-05
10,491	Reducing Tail Latency in Storage-Disaggregated Database Systems	2026	SIGMOD	5.093636e-05
10,616	Terark-DS: A High-Performance and Storage-Efficient Key-Value Separation Storage Engine on Disaggregated Storage	2026	VLDB	5.093636e-05
10,955	DobLIX: A Dual-Objective Learned Index for Log-Structured Merge Trees	2025	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 15 of 15 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
73	Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases	2017	SIGMOD	0.00037333356
426	The LDBC Social Network Benchmark: Interactive Workload	2015	SIGMOD	0.00018692185
831	Dostoevsky: Better Space-Time Trade-Offs for LSM-Tree Based Key-Value Stores via Adaptive Removal of Superfluous Merging	2018	SIGMOD	0.00013748512
880	SuRF: Practical Range Query Filtering with Fast Succinct Tries	2018	SIGMOD	0.00013432693
1,502	The Log-Structured Merge-Bush & the Wacky Continuum	2019	SIGMOD	0.00010557694
1,580	Compaction management in distributed key-value datastores	2015	VLDB	0.00010299919
1,954	Chucky: A Succinct Cuckoo Filter for LSM-Tree	2021	SIGMOD	9.4208165e-05
2,698	Rosetta: A Robust Space-Time Optimized Range Filter for Key-Value Stores	2020	SIGMOD	8.2450522e-05
3,054	Spooky: Granulating LSM-Tree Compactions Correctly	2022	VLDB	7.8090808e-05
3,100	Rethinking Data Management Systems for Disaggregated Data Centers	2020	CIDR	7.7608255e-05
3,758	Nova-LSM: A Distributed, Component-based LSM-tree Key-value Store	2021	SIGMOD	7.1471346e-05
3,773	SplinterDB and Maplets: Improving the Tradeoffs in Key-Value Store Compaction Policy	2023	SIGMOD	7.1384476e-05
4,200	Disaggregating RocksDB: A Production Experience	2023	SIGMOD	6.835902e-05
5,196	Optimizing Data-intensive Systems in Disaggregated Data Centers with TELEPORT	2022	SIGMOD	6.3230009e-05
7,341	Understanding the Performance Implications of the Design Principles in Storage-Disaggregated Databases	2024	SIGMOD	5.6390976e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	857	SlimDB: A Space-Efficient Key-Value Storage Engine For Semi-Sorted Data	2017	VLDB
2	6,828	Breaking Down Memory Walls in LSM-based Storage Systems	2020	SIGMOD
3	10,465	Improving Range Scan Performance in LSM-trees with Group Caching	2026	SIGMOD
4	5,780	Compactionary: A Dictionary for LSM Compactions	2022	SIGMOD
5	8,919	MirrorKV: An Efficient Key-Value Store on Hybrid Cloud Storage with Balanced Performance of Compaction and Querying	2023	SIGMOD
6	1,580	Compaction management in distributed key-value datastores	2015	VLDB
7	3,005	Constructing and Analyzing the LSM Compaction Design Space	2021	VLDB
8	10,471	Making LSM-Tree-based Key-Value Store Practical and Efficient for Multi-Tenant Serverless Cloud Databases	2026	SIGMOD
9	3,758	Nova-LSM: A Distributed, Component-based LSM-tree Key-value Store	2021	SIGMOD
10	10,274	O3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer Offloading	2026	SIGMOD