# Deploying a Steered Query Optimizer in Production at Microsoft

arXiv: https://arxiv.org/abs/2210.13625 · HTML: https://mlsanity.com/paper/2210.13625/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 54 references that are in the map.
- First posted on arXiv 24 Oct 2022.

## Builds on (most cited first, 13 of 13)

- [Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits](https://mlsanity.com/paper/1402.0555/) (2014)
- [The Case for Learned Index Structures](https://mlsanity.com/paper/1712.01208/) (2017)
- [Optimal and Adaptive Off-policy Evaluation in Contextual Bandits](https://mlsanity.com/paper/1612.01205/) (2016)
- [Adapting to Misspecification in Contextual Bandits](https://mlsanity.com/paper/2107.05745/) (2021)
- [Neo: A Learned Query Optimizer](https://mlsanity.com/paper/1904.03711/) (2019)
- [Bao: Learning to Steer Query Optimizers](https://mlsanity.com/paper/2004.03814/) (2020)
- [Learning to Optimize Join Queries With Deep Reinforcement Learning](https://mlsanity.com/paper/1808.03196/) (2018)
- [Deep Reinforcement Learning for Join Order Enumeration](https://mlsanity.com/paper/1803.00055/) (2018)
- [Cost Models for Big Data Query Processing: Learning, Retrofitting, and Our Findings](https://mlsanity.com/paper/2002.12393/) (2020)
- [MLOS: An Infrastructure for Automated Software Performance Engineering](https://mlsanity.com/paper/2006.02155/) (2020)
- [Optimal Resource Allocation for Serverless Queries](https://mlsanity.com/paper/2107.08594/) (2021)
- [Resonance: Replacing Software Constants with Context-Aware Models in Real-time Communication](https://mlsanity.com/paper/2011.12715/) (2020)
- [Phoebe: A Learning-based Checkpoint Optimizer](https://mlsanity.com/paper/2110.02313/) (2021)

## Built on by (most cited first, 2 of 2)

- [ML-Powered Index Tuning: An Overview of Recent Progress and Open Challenges](https://mlsanity.com/paper/2308.13641/) (2023)
- [Low Rank Learning for Offline Query Optimization](https://mlsanity.com/paper/2504.06399/) (2025)

## Abstract (arXiv)

Modern analytical workloads are highly heterogeneous and massively complex, making generic query optimizers untenable for many customers and scenarios. As a result, it is important to specialize these optimizers to instances of the workloads. In this paper, we continue a recent line of work in steering a query optimizer towards better plans for a given workload, and make major strides in pushing previous research ideas to production deployment. Along the way we solve several operational challenges including, making steering actions more manageable, keeping the costs of steering within budget, and avoiding unexpected performance regressions in production. Our resulting system, QQ-advisor, essentially externalizes the query planner to a massive offline pipeline for better exploration and specialization. We discuss various aspects of our design and show detailed results over production SCOPE workloads at Microsoft, where the system is currently enabled by default.