Work

Are Learned DBMS Components Robust to Workload Drift?: [Experiments & Analysis]

Year: 2026

Type: article

Abstract: Workload-driven learned database components leverage historical query workloads to build predictive models. These models typically take queries or query plans as input and generate predictions or decisions to optimize query performance. However, the effectiveness of these models heavily depends on the quality and distribution of the training query workload (training workload). While prior studies focus on scenarios where the test query workload (test workload) distribution matches that of the training workload, real-world workloads often change over time, leading to workload distribution drift. In this paper, we explore the impact of workload drift on workload-driven models across different database components. We generate a variety of workload drift scenarios based on IMDb and STATS datasets, and analyze how different levels and types of drift affect estimation performance of each component and overall query execution performance 1 . Our findings highlight the limitations of current workload-driven models under workload drift and provide insights into designing more robust and adaptive solutions.

Source: Proceedings of the ACM on Management of Data

DOI: 10.1145/3802014

Authors: Zizhong Meng, Gao Cong, Siqiang Luo

Institution: Nanyang Technological University

Language: English

Topic: Advanced Database Systems and Queries

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Ministry of Education - Singapore

Awards: G5502671339, G660158539, G8263586710