Buffer Pool Aware Query Scheduling via Deep Reinforcement Learning
This addresses query performance optimization in databases, though it appears incremental as an application of existing ML techniques to a specific database problem.
The researchers tackled the problem of query scheduling to reduce disk reads and improve query performance by introducing SmartQueue, a learned scheduler that uses deep reinforcement learning to create workload-specific strategies. Their proof-of-concept prototype demonstrated significant performance improvements over hand-crafted scheduling heuristics.
In this extended abstract, we propose a new technique for query scheduling with the explicit goal of reducing disk reads and thus implicitly increasing query performance. We introduce SmartQueue, a learned scheduler that leverages overlapping data reads among incoming queries and learns a scheduling strategy that improves cache hits. SmartQueue relies on deep reinforcement learning to produce workload-specific scheduling strategies that focus on long-term performance benefits while being adaptive to previously-unseen data access patterns. We present results from a proof-of-concept prototype, demonstrating that learned schedulers can offer significant performance improvements over hand-crafted scheduling heuristics. Ultimately, we make the case that this is a promising research direction at the intersection of machine learning and databases.