---
title: "打破数据库锁定：基于LLM的高性能存储读取器自动生成方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.07696v1"
permalink: "https://feed.astralor.com/items/itm_3203b0893ebc14b725f23dae"
published: "2026-07-08T17:55:00.000Z"
score: 78
channel: "ai"
tags: ["Apache Arrow","Jailbreak","PostgreSQL","TPC-H","大语言模型","数据库旁路"]
---

# 打破数据库锁定：基于LLM的高性能存储读取器自动生成方法

## AI 点评

> 这篇论文让我眼前一亮：将LLM的代码生成能力直接用在数据库存储格式解析上，巧妙绕开了传统驱动的性能陷阱。对数据工程师来说，这是提升分析效率的利器；对研究者，它开辟了AI与系统性能优化的新交叉方向。特别推荐给正在解决大数据管道中数据库瓶颈的团队。

## 速览

该论文提出Jailbreak方法，利用LLM从数据库源代码和文档中学习文件格式，自动生成高性能存储读取器，绕过JDBC/ODBC等驱动层直接读取数据库存储文件，并转化为列式内存缓冲。在TPC-H基准测试中，该方法在完整查询结果正确性验证下，实现高达27倍的端到端分析吞吐量提升。实验覆盖PostgreSQL和MySQL，证明了LLM辅助代码生成在打破数据库锁定方面的可行性与通用性。

## 关键点

- Jailbreak方法利用LLM自动生成数据库存储读取器，绕过传统驱动层直接访问存储文件，实现高性能列式数据获取。
- 在TPC-H基准测试中，与JDBC/ODBC基线相比，端到端分析吞吐量提升高达27倍。
- 方法适用于任何文件格式可通过文档或源码获取的数据库系统，通用性强。
- 生成的Apache Arrow缓冲可直接被DuckDB、Apache Spark、cuDF等主流查询引擎消费。

## 全文

Analytical workloads operating on data stored in external database systems face a fundamental bottleneck: data access is guarded entirely by the database driver, like JDBC or ODBC, forcing all reads through query execution and other driver layers that are not designed for bulk columnar analytics. We present Jailbreak, an approach that bypasses the database engine entirely by reading storage files directly and materializing data as in-memory columnar buffers. Jailbreak's key insight is that database file formats, while complex, are fully specified by their source code and documentation, artifacts that Large Language Models (LLMs) can ingest to regenerate operator-specific table reading components without human-engineered parsing logic. Jailbreak leverages LLM-assisted code synthesis for database storage decoding, turning a traditionally opaque format into a directly queryable artifact. We evaluate Jailbreak on PostgreSQL and MySQL storage files, targeting analytical snapshot scenarios common in read replicas and offline processing pipelines. The generated reader produces Apache Arrow buffers consumable directly by most of the widely known query engines, including DuckDB, Apache Spark, and GPU-accelerated frameworks such as cuDF and Spark RAPIDS. We validate correctness against JDBC/ODBC-based baselines using the TPC-H benchmark across all query results, and demonstrate significant performance improvements in end-to-end analytical throughput, achieving up to 27x speedups. Our results showcase that LLM-assisted storage reader synthesis is a viable and generalizable methodology for breaking data lock-in across database systems, with applications beyond PostgreSQL and MySQL for any system whose file format is available to the LLM from documentation or source code.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_3203b0893ebc14b725f23dae