Optimus: Deployable Query Optimization via Novel SQL Rewrites

Raahim Lone

Keywords: Learned Query Optimization, guard-checked rewrites, deployability, LLM-mined rewrites

TLDR: Optimus is a deployable learned query optimizer for PostgreSQL that uses novel, guard-checked SQL query rewrites to achieve a 1.16x speedup.

Abstract: Learned database query optimizers typically optimize over a set of configurations, which limits the attainable plan space. Optimus expands the action space itself by mining novel execution plan rewrites and learns to select among these actions online. Optimus utilizes graph-based inductive matrix completion and a multilayer perceptron with the objective of minimizing latency. Crucially, the system is deployable by design: it requires no engine modifications and its rules include guard-checked compilation. On the extended JOB benchmark, Optimus yields a speedup of 1.16x over vanilla PostgreSQL solely using novel rewrites.

Submission Number: 17