AXE: A Task Decomposition Approach to Learned LSM Tuning

Summary: AXE decomposes LSM tuning into learned cost modeling plus a tuner trained on unlimited synthetic samples, avoiding deployment-time retraining and handling categorical knobs. It scales across instances and environments, achieving higher performance than Bayesian Optimization 71% of the time with 100× lower overhead. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID: hcfa25aa2fa690148
Venue: VLDB
Year: 2025
Pagerank: 4.9769913e-05
Overall Rank: 11,436 | 23.14%
DOI: 10.14778/3773731.3773735
PDF: Download (CC BY-NC-ND 4.0)

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Andy Huynh (Boston University)
2. Anwesha Saha (Boston University)
3. Harshal A. Chaudhari (Boston University)
4. Manos Athanassoulis (Boston University)

BibTeX Citation

@article{huynh_vldb25,
        title = {{AXE: A Task Decomposition Approach to Learned LSM Tuning}},
        author = {Huynh, Andy and Saha, Anwesha and Chaudhari, Harshal A. and Athanassoulis, Manos},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {13},
        pages = {5582--5595},
        doi = {10.14778/3773731.3773735},
        url = {https://doi.org/10.14778/3773731.3773735},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 30 of 30 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
78	Automatic Database Management System Tuning Through Large-scale Machine Learning	2017	SIGMOD	0.00036675568
88	Automated Selection of Materialized Views and Indexes for SQL Databases	2000	VLDB	0.00035340164
151	An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server	1997	VLDB	0.00028664776
252	Database Cracking	2007	CIDR	0.00023101361
314	An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning	2019	SIGMOD	0.00021276452
400	Monkey: Optimal Navigable Key-Value Store	2017	SIGMOD	0.00019124757
437	QTune: A Query-Aware Database Tuning System with Deep Reinforcement Learning	2019	VLDB	0.00018310278
462	An End-to-End Learning-based Cost Estimator	2020	VLDB	0.00017836105
753	Dostoevsky: Better Space-Time Trade-Offs for LSM-Tree Based Key-Value Stores via Adaptive Removal of Superfluous Merging	2018	SIGMOD	0.00014232329
921	AsterixDB: A Scalable, Open Source BDMS	2014	VLDB	0.00013064043
1,147	MyRocks: LSM-Tree Database Storage Engine Serving Facebook's Social Graph	2020	VLDB	0.00011810023
1,606	The Data Calculator*: Data Structure Design and Cost Synthesis from First Principles and Learned Cost Models	2018	SIGMOD	0.00010091937
1,891	Design Continuums and the Path Toward Self-Designing Key-Value Stores that Know and Learn	2019	CIDR	9.4233024e-05
2,721	ResTune: Resource Oriented Tuning Boosted by Meta-Learning for Cloud Databases	2021	SIGMOD	8.0931221e-05
2,770	Facilitating Database Tuning with Hyper-Parameter Optimization: A Comprehensive Experimental Evaluation	2022	VLDB	8.0343719e-05
2,833	Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings	2020	SIGMOD	7.9539771e-05
3,052	LlamaTune: Sample-Efficient DBMS Configuration Tuning	2022	VLDB	7.704739e-05
3,480	Cosine: A Cloud-Cost Optimized Self-Designing Key-Value Storage Engine	2022	VLDB	7.2661848e-05
3,979	Efficient Deep Learning Pipelines for Accurate Cost Estimations Over Large Scale Query Workload	2021	SIGMOD	6.8791817e-05
4,536	One Model to Rule them All: Towards Zero-Shot Learning for Databases	2022	CIDR	6.552998e-05
4,571	COLT: Continuous On-Line Database Tuning	2006	SIGMOD	6.5269069e-05
5,250	Endure: A Robust Tuning Paradigm for LSM Trees Under Workload Uncertainty	2022	VLDB	6.2092552e-05
5,879	Compactionary: A Dictionary for LSM Compactions	2022	SIGMOD	5.9587188e-05
6,081	From Auto-tuning One Size Fits All to Self-designed and Learned Data-intensive Systems	2019	SIGMOD	5.8897947e-05
6,123	Learning to Optimize LSM-trees: Towards A Reinforcement Learning based Key-Value Store for Dynamic Workloads	2023	SIGMOD	5.8771312e-05
6,254	Foundations of Automated Database Tuning	2006	VLDB	5.8328094e-05
7,021	Rethinking Learned Cost Models: Why Start from Scratch?	2023	SIGMOD	5.6168049e-05
7,909	CAMAL: Optimizing LSM-trees via Active Learning	2024	SIGMOD	5.4266123e-05
9,191	Structural Designs Meet Optimality: Exploring Optimized LSM-tree Structures in A Colossal Configuration Space	2024	SIGMOD	5.20942e-05
9,440	MLOS in Action: Bridging the Gap Between Experimentation and Auto-Tuning in the Cloud	2024	VLDB	5.1759149e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	8,538	SA-LSM: Optimize Data Layout for LSM-tree Based Storage using Survival Analysis	2022	VLDB
2	9,140	Rethinking The Compaction Policies in LSM-trees	2025	SIGMOD
3	3,052	LlamaTune: Sample-Efficient DBMS Configuration Tuning	2022	VLDB
4	2,996	Accordion: Better Memory Organization for LSM Key-Value Stores	2018	VLDB
5	5,041	Dissecting, Designing, and Optimizing LSM-based Data Stores	2022	SIGMOD
6	817	SlimDB: A Space-Efficient Key-Value Storage Engine For Semi-Sorted Data	2017	VLDB
7	7,909	CAMAL: Optimizing LSM-trees via Active Learning	2024	SIGMOD
8	5,250	Endure: A Robust Tuning Paradigm for LSM Trees Under Workload Uncertainty	2022	VLDB
9	5,022	Breaking Down Memory Walls: Adaptive Memory Management in LSM-based Storage Systems	2021	VLDB
10	7,593	Efficient Data Ingestion and Query Processing for LSM-Based Storage Systems	2019	VLDB