Query Performance Explanation through Large Language Model for HTAP Systems

TL;DR

This paper introduces a framework using large language models to generate understandable explanations for query performance differences in HTAP systems, aiding non-experts in performance analysis.

Contribution

It presents a novel retrieval-augmented generation framework that combines knowledge bases and query plan embeddings to improve performance explanations in hybrid database systems.

Findings

Effective retrieval of relevant knowledge using tree-CNN classifier

Generation of clear, context-aware explanations for query performance

Potential to enhance database optimization and user support

Abstract

In hybrid transactional and analytical processing (HTAP) systems, users often struggle to understand why query plans from one engine (OLAP or OLTP) perform significantly slower than those from another. Although optimizers provide plan details via the EXPLAIN function, these explanations are frequently too technical for non-experts and offer limited insights into performance differences across engines. To address this, we propose a novel framework that leverages large language models (LLMs) to explain query performance in HTAP systems. Built on Retrieval-Augmented Generation (RAG), our framework constructs a knowledge base that stores historical query executions and expert-curated explanations. To enable efficient retrieval of relevant knowledge, query plans are embedded using a lightweight tree-CNN classifier. This augmentation allows the LLM to generate clear, context-aware explanations of performance differences between engines. Our approach demonstrates the potential of LLMs in hybrid engine systems, paving the way for further advancements in database optimization and user support.