Containerized Execution of UDFs: An Experimental Evaluation

Summary: First study spanning containerized UDF life cycle, bottlenecks, and cross-engine extensibility for arbitrary-language UDFs. Binary-based communication cuts overhead (>2.4x vs text); Arrow Flight near-native speeds; start-up times 0.07–7s. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 12985
Venue: VLDB
Year: 2022
Pagerank: 5.8417517e-05
Overall Rank: 6,553 | 55.05%
DOI: 10.14778/3551793.3551860

Incoming Non-self Citations Over Time

Authors

1. Karla Saur (Microsoft)
2. Tara Mirmira (University of California San Diego)
3. Konstantinos Karanasos (Meta)
4. Jesús Camacho-Rodríguez (Microsoft)

BibTeX Citation

@article{saur_vldb22,
        title = {{Containerized Execution of UDFs: An Experimental Evaluation}},
        author = {Saur, Karla and Mirmira, Tara and Karanasos, Konstantinos and Camacho-Rodríguez, Jesús},
        journal = {PVLDB},
        series = {{VLDB} '22},
        volume = {15},
        number = {11},
        pages = {3158--3171},
        doi = {10.14778/3551793.3551860},
        url = {https://doi.org/10.14778/3551793.3551860},
        year = {2022}
}

Incoming Citations (Sorted by Pagerank)

Showing 4 of 4 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,847	Biathlon: Harnessing Model Resilience for Accelerating ML Inference Pipelines	2024	VLDB	5.5330423e-05
8,193	Towards Building Autonomous Data Services on Azure	2023	SIGMOD	5.4696038e-05
9,127	Databricks Lakeguard: Supporting Fine-grained Access Control and Multi-user Capabilities for Apache Spark Workloads	2025	SIGMOD	5.3189314e-05
10,057	AnyBlox: A Framework for Self-Decoding Datasets	2025	VLDB	5.1664022e-05

Outgoing Citations (Sorted by Pagerank)

Showing 12 of 12 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
520	Delta Lake: High-Performance ACID Table Storage over Cloud Object Stores	2020	VLDB	0.00017136828
894	Froid: Optimization of Imperative Programs in a Relational Database	2018	VLDB	0.00013367658
1,442	An Architecture for Compiling UDF-centric Workflows	2015	VLDB	0.00010778486
1,482	Cloudburst: Stateful Functions-as-a-Service	2020	VLDB	0.00010642079
1,768	Tuplex: Data Science in Python at Native Code Speed	2021	SIGMOD	9.8041636e-05
2,025	Data Market Platforms: Trading Data Assets to Solve Data Problems	2020	VLDB	9.2903125e-05
2,164	Opening the Black Boxes in Data Flow Optimization	2012	VLDB	9.0521951e-05
2,293	Extending Relational Query Processing with ML Inference	2020	CIDR	8.7949378e-05
2,865	End-to-end Optimization of Machine Learning Prediction Queries	2022	SIGMOD	8.0180243e-05
4,292	Putting Pandas in a Box	2021	CIDR	6.7784325e-05
5,301	Babelfish: Efficient Execution of Polyglot Queries	2022	VLDB	6.2750553e-05
5,791	Accelerating Python UDFs in Vectorized Query Execution	2022	CIDR	6.0873094e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	9,415	The Key to Effective UDF Optimization: Before Inlining, First Perform Outlining	2025	VLDB
2	1,442	An Architecture for Compiling UDF-centric Workflows	2015	VLDB
3	6,314	YeSQL: "You extend SQL" with Rich and Highly Performant User-Defined Functions in Relational Databases	2022	VLDB
4	12,510	Fast and Dynamic OLAP Exploration Using UDFs	2009	SIGMOD
5	6,328	Functional-Style SQL UDFs With a Capital 'F'	2020	SIGMOD
6	6,015	Dear User-Defined Functions, Inlining isn't working out so great for us. Let's try batching to make our relationship work. Sincerely, SQL	2024	CIDR
7	5,791	Accelerating Python UDFs in Vectorized Query Execution	2022	CIDR
8	10,740	UDFBench: A Tool for Benchmarking UDF Queries on SQL Engines	2025	SIGMOD
9	8,096	Efficient Execution of User-Defined Functions in SQL Queries	2023	VLDB
10	9,917	The UDFBench Benchmark for General-purpose UDF Queries	2025	VLDB