A Case for Agentic Tuning: From Documentation to Action in PostgreSQL
For database administrators and system tuners, this work addresses the gap between static tuning guides and dynamic, workload-aware optimization, offering a practical improvement over existing methods.
The paper identifies limitations of static documentation for system tuning and proposes PerfEvolve, an LLM-based agent that uses executable skills for dynamic tuning. On PostgreSQL with TPC-C and TPC-H benchmarks, PerfEvolve outperforms documentation-driven baselines by up to 35.2%.
Documentation has long guided computer system tuning by distilling expert knowledge into per-parameter recommendations. Yet such guides capture only what experts conclude, discarding how they reason. This fundamental gap manifests in three concrete deficiencies: documentation grows stale as software evolves, fails under heterogeneous workloads, and ignores inter-parameter dependencies. We propose shifting from static documentation to dynamic action for system tuning. We introduce PerfEvolve, which translates expert tuning methodologies into executable skills that equip LLM-based agents to perform version-consistency verification, workload-specific profiling, and multi-parameter joint optimization. Evaluated on PostgreSQL under TPC-C and TPC-H benchmarks, PerfEvolve outperforms state-of-the-art documentation-driven tuning baselines by up to 35.2%. The tool is available at https://github.com/ISCAS-OSLab/PerfEvolve.