DBScholar

Back to papers

Spooky: Granulating LSM-Tree Compactions Correctly

Summary: Spooky exposes the opposing costs of LSM compaction granularity: Full Merge causes space amplification, while Partial Merge causes write amplification and SSD GC overhead. It aligns lower-level partitions to largest-level file boundaries, achieving >2× lower space and write amplification than either strategy. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
hb9e54de705162b42
Venue
VLDB
Year
2022
Pagerank
7.894356e-05
Overall Rank
2,882 | 80.69%
DOI
10.14778/3551793.3551853
PDF
Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{dayan_vldb22,
        title = {{Spooky: Granulating LSM-Tree Compactions Correctly}},
        author = {Dayan, Niv and Weiss, Tamar and Dashevsky, Shmuel and Pan, Michael and Bortnikov, Edward and Twitto, Moshe},
        journal = {PVLDB},
        series = {{VLDB} '22},
        volume = {15},
        number = {11},
        pages = {3071--3084},
        doi = {10.14778/3551793.3551853},
        url = {https://doi.org/10.14778/3551793.3551853},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 25 of 25 citing papers.

Rank Citing Paper Year Venue Pagerank
4,771 GRF: A Global Range Filter for LSM-Trees with Shape Encoding 2024 SIGMOD 6.412225e-05
5,082 InfiniFilter: Expanding Filters to Infinity and Beyond 2023 SIGMOD 6.2679091e-05
6,137 Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloads 2023 SIGMOD 5.8576977e-05
7,258 CaaS-LSM: Compaction-as-a-Service for LSM-based Key-Value Stores in Storage Disaggregated Infrastructure 2024 SIGMOD 5.5577384e-05
7,925 CAMAL: Optimizing LSM-trees via Active Learning 2024 SIGMOD 5.4086685e-05
8,245 ArceKV: Towards Workload-driven LSM-compactions for Key-Value Store Under Dynamic Workloads 2026 VLDB 5.3556365e-05
8,342 How to Grow an LSM-tree? Towards Bridging the Gap Between Theory and Practice 2025 SIGMOD 5.3345258e-05
8,666 Mnemosyne: Dynamic Workload-Aware BF Tuning via Accurate Statistics in LSM trees 2025 SIGMOD 5.277223e-05
8,976 Practical Dynamic Extension for Sampling Indexes 2023 SIGMOD 5.2343756e-05
9,084 Aster: Enhancing LSM-structures for Scalable Graph Database 2025 SIGMOD 5.2097768e-05
9,111 MirrorKV: An Efficient Key-Value Store on Hybrid Cloud Storage with Balanced Performance of Compaction and Querying 2023 SIGMOD 5.208561e-05
9,162 Rethinking The Compaction Policies in LSM-trees 2025 SIGMOD 5.2035666e-05
9,215 Structural Designs Meet Optimality: Exploring Optimized LSM-tree Structures in A Colossal Configuration Space 2024 SIGMOD 5.1921944e-05
9,681 Are Joins over LSM-trees Ready? Take RocksDB as an Example 2025 VLDB 5.1258854e-05
10,073 LavaStore: ByteDance's Purpose-built, High-performance, Cost-effective Local Storage Engine for Cloud Services 2024 VLDB 5.0732737e-05
10,264 From FASTER to F2: Evolving Concurrent Key-Value Store Designs for Large Skewed Workloads 2025 VLDB 5.0380426e-05
10,434 A Multi-tenant Relational OLTP Database at Salesforce 2026 CIDR 4.9605343e-05
10,563 O3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer Offloading 2026 SIGMOD 4.9605343e-05
10,631 Counting Is All You Need for Instant Tuple Discovery: Enabling Real-Time HTAP in Standalone DBMSs 2026 SIGMOD 4.9605343e-05
10,730 Making LSM-Tree-based Key-Value Store Practical and Efficient for Multi-Tenant Serverless Cloud Databases 2026 SIGMOD 4.9605343e-05
10,739 PartitionKV: Redesigning LSM-tree KV Stores on NVMs with Adaptive Partitioning for Reducing Write Stalls and Amplification 2026 SIGMOD 4.9605343e-05
10,796 How to Write to SSDs 2026 VLDB 4.9605343e-05
10,835 Kirin: Efficient In-Storage Learned Compaction for LSM-Trees via System-Algorithm Co-Design 2026 VLDB 4.9605343e-05
10,915 Rethinking Learned Index and LSM-tree Integration 2026 VLDB 4.9605343e-05
11,640 On Reducing Space Amplification with Multi-Column Compaction in Apache IoTDB 2024 VLDB 4.9605343e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 27 of 27 cited papers.

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

Rank Cited Paper Year Venue Pagerank
261 bLSM: A General Purpose Log Structured Merge Tree 2012 SIGMOD 0.00022862412
402 Monkey: Optimal Navigable Key-Value Store 2017 SIGMOD 0.00019070605
438 Optimizing Space Amplification in RocksDB 2017 CIDR 0.00018259155
487 BLOCKBENCH: A Framework for Analyzing Private Blockchains 2017 SIGMOD 0.00017413439
761 Dostoevsky: Better Space-Time Trade-Offs for LSM-Tree Based Key-Value Stores via Adaptive Removal of Superfluous Merging 2018 SIGMOD 0.00014191047
814 SlimDB: A Space-Efficient Key-Value Storage Engine For Semi-Sorted Data 2017 VLDB 0.00013697533
892 SuRF: Practical Range Query Filtering with Fast Succinct Tries 2018 SIGMOD 0.00013207671
1,077 Cache-Oblivious String B-trees 2006 PODS 0.00012122621
1,147 MyRocks: LSM-Tree Database Storage Engine Serving Facebook's Social Graph 2020 VLDB 0.00011777851
1,310 Realtime Data Processing at Facebook 2016 SIGMOD 0.00011065568
1,324 X-Engine: An Optimized Storage Engine for Large-scale E-commerce Transaction Processing 2019 SIGMOD 0.00011019001
1,429 The Log-Structured Merge-Bush & the Wacky Continuum 2019 SIGMOD 0.00010685393
1,572 Compaction management in distributed key-value datastores 2015 VLDB 0.00010174039
1,611 The Data Calculator*: Data Structure Design and Cost Synthesis from First Principles and Learned Cost Models 2018 SIGMOD 0.00010066379
1,900 Design Continuums and the Path Toward Self-Designing Key-Value Stores that Know and Learn 2019 CIDR 9.3926585e-05
1,991 Chucky: A Succinct Cuckoo Filter for LSM-Tree 2021 SIGMOD 9.2264312e-05
2,780 Constructing and Analyzing the LSM Compaction Design Space 2021 VLDB 8.0073289e-05
2,796 Lethe: A Tunable Delete-Aware LSM Engine 2020 SIGMOD 7.9849253e-05
3,012 Accordion: Better Memory Organization for LSM Key-Value Stores 2018 VLDB 7.7414696e-05
3,140 Improving Flash Write Performance by Using Update Frequency 2013 VLDB 7.5864047e-05
4,693 Coconut: A Scalable Bottom-Up Approach for Building Data Series Indexes 2018 VLDB 6.4490657e-05
5,967 The Necessary Death of the Block Device Interface 2013 CIDR 5.913895e-05
6,255 Toward a Better Understanding and Evaluation of Tree Structures on Flash SSDs 2021 VLDB 5.8165041e-05
7,062 Coconut Palm: Static and Streaming Data Series Exploration Now in your Palm 2019 SIGMOD 5.593733e-05
7,411 GeckoFTL: Scalable Flash Translation Techniques For Very Large Flash Devices 2016 SIGMOD 5.5164757e-05
9,698 The End of Moore’s Law and the Rise of The Data Processor 2021 VLDB 5.1258854e-05
14,004 EagleTree: Exploring the Design Space of SSD-Based Algorithms 2013 VLDB -
Previous Page 1 / 1 Next

Semantically Similar Papers

# Overall Rank Paper Year Venue
1 11,640 On Reducing Space Amplification with Multi-Column Compaction in Apache IoTDB 2024 VLDB
2 814 SlimDB: A Space-Efficient Key-Value Storage Engine For Semi-Sorted Data 2017 VLDB
3 6,954 Breaking Down Memory Walls in LSM-based Storage Systems 2020 SIGMOD
4 10,215 DumpKV: Learning based lifetime aware garbage collection for key value separation in LSM-tree 2025 VLDB
5 1,429 The Log-Structured Merge-Bush & the Wacky Continuum 2019 SIGMOD
6 10,739 PartitionKV: Redesigning LSM-tree KV Stores on NVMs with Adaptive Partitioning for Reducing Write Stalls and Amplification 2026 SIGMOD
7 5,894 Compactionary: A Dictionary for LSM Compactions 2022 SIGMOD
8 12,257 Splaying Log-Structured Merge-Trees 2018 SIGMOD
9 9,162 Rethinking The Compaction Policies in LSM-trees 2025 SIGMOD
10 2,780 Constructing and Analyzing the LSM Compaction Design Space 2021 VLDB