PBench: Workload Synthesizer with Real Statistics for Cloud Analytics Benchmarking

Yan Zhou, Chunwei Liu, B. Urgaonkar, Zhengle Wang, M. Mueller, Chao Zhang, Songyue Zhang, Pascal Pfeil, Dominik Horn, Zhengchun Liu, Davide Pagano, Tim Kraska, Samuel Madden, Ju Fan. 2025. Proceedings of the VLDB Endowment.

Read the paper · doi:10.14778/3749646.3749661 · arXiv:2506.16379

What this paper does with SQLancer

One citation, listing database benchmarking among the uses a synthetic workload serves, with SQLancer's work among the references. PBench synthesises analytics workloads that reproduce the execution statistics of real cloud workloads. Standard benchmarks use fixed query patterns and miss production behaviour, while released traces lack the queries and databases needed to be benchmarks. PBench selects and combines components from existing benchmarks and augments them with new ones, using multi-objective optimisation, timestamp assignment for temporal dynamics, and LLM-generated components. It cuts approximation error by up to 6x. Written by claude-opus-5 from the 1 place this paper refers to SQLancer. The quotations below are the paper's own words, stored verbatim when the text was extracted.

How it was classified

uses infrastructure — no

SQLancer is cited, not used; nothing in the mentions describes reusing its code.

extends technique — no

No technique is extended; the citation is background.

compares with — no

No empirical comparison against SQLancer is reported in the mentions.

describes as state of the art — no

The citation does not characterise SQLancer as the state of the art.

SQLancer publications it cites (1)

Bibliography entries that resolved to a SQLancer publication, or to a paper by one of the project's authors. A sentence citing one of these numbers is a reference to SQLancer even when it never writes the name.

#	Entry	Matched as
2	Jinsheng Ba and Manuel Rigger. 2024. Keep It Simple: Testing Databases via Differential Query Plans. Proceedings of the ACM on Management of Data 2, 3 (2024), 1–26.	sqlancer publication · DQP

Every place it refers to SQLancer (1)

1 sentence, each stored verbatim from the extracted text with where it was found and how. “Citation marker” means the sentence names no tool at all and was reached through a reference number that resolved to a SQLancer publication.

Id	Sentence	Found by	Where
M1	Then, the generated synthetic workload offers an effective solution for database benchmarking [ 8,35,36], performance tuning [ 28], and bug detection [ 2], allowing database developers to perform realistic evaluations while preserving customer privacy and avoiding exposure of sensitive workloads or data.	citation marker background	2.2 Problem Formalization page 4

This page is rendered from _data/papers/paper_doi_10_14778_3749646_3749661.json, extracted from arxiv. 13 pages, 38 references parsed.