BARQ: A Vectorized SPARQL Query Execution Engine

2025-04-06

AI Summary

SPARQL query performance on the Stardog knowledge graph platform suffers from severe CPU bottlenecks in CPU-intensive workloads, while the traditional Volcano execution model fails to simultaneously optimize for disk I/O-bound and OLTP-style queries. Method: This paper proposes BARQ—the first vectorized query execution framework designed for industrial-grade SPARQL engines. BARQ refactors critical operators (especially joins) using a batched vectorized paradigm and introduces a progressive integration mechanism enabling seamless deployment without modifying existing query interfaces. It further innovates with a CPU/disk-bound adaptive hybrid execution mode. Contribution/Results: BARQ delivers significant acceleration for CPU-intensive queries—reducing end-to-end latency by over 40% on average—while preserving full performance for disk-intensive and OLTP-style queries, thus achieving substantial speedups without compromising compatibility or generality.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Distributed Search
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Stardog is a commercial Knowledge Graph platform built on top of an RDF graph database whose primary means of communication is a standardized graph query language called SPARQL. This paper describes our journey of developing a more performant query execution layer and plugging it into Stardog's query engine. The new executor, called BARQ, is based on the known principle of processing batches of tuples at a time in most critical query operators, particularly joins. In addition to presenting BARQ, the paper describes the challenges of integrating it into a mature, tightly integrated system based on the classical tuple-at-a-time Volcano model. It offers a gradual approach to overcoming the challenges that small- to medium-size engineering teams typically face. Finally, the paper presents experimental results showing that BARQ makes Stardog substantially faster on CPU-bound queries without sacrificing performance on disk-bound and OLTP-style queries.

Problem

• Enhancing SPARQL query performance in Stardog
• Integrating batch-based execution into Volcano model
• Balancing speed for CPU-bound and disk-bound queries

Innovation

• Vectorized batch processing for SPARQL queries
• Integration with existing tuple-at-a-time system
• Performance boost for CPU-bound queries