Improving DBMS Scheduling Decisions with Fine-grained Performance Prediction on Concurrent Queries -- Extended

2025-01-27

AI Summary

Existing non-intrusive query schedulers rely on coarse-grained, static computational models, limiting their adaptability to dynamic workloads and resulting in high aggregate query waiting times and pronounced tail latency. This paper introduces IconqSched—the first non-intrusive query scheduler leveraging black-box, fine-grained performance prediction. Its core contributions are: (1) the Iconq predictor, which accurately models the fine-grained interactions between system state and individual queries—without modifying the DBMS—to estimate execution latency; and (2) a lightweight runtime feature extraction mechanism coupled with a greedy online scheduling algorithm that dynamically optimizes query submission order and timing to minimize end-to-end latency (queuing + execution). Evaluated on PostgreSQL and Amazon Redshift, IconqSched reduces average latency by 10.3%–28.2% and tail latency (95th percentile) by 14.9%–38.9% compared to state-of-the-art baselines.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

Query scheduling is a critical task that directly impacts query performance in database management systems (DBMS). Deeply integrated schedulers, which require changes to DBMS internals, are usually customized for a specific engine and can take months to implement. In contrast, non-intrusive schedulers make coarse-grained decisions, such as controlling query admission and re-ordering query execution, without requiring modifications to DBMS internals. They require much less engineering effort and can be applied across a wide range of DBMS engines, offering immediate benefits to end users. However, most existing non-intrusive scheduling systems rely on simplified cost models and heuristics that cannot accurately model query interactions under concurrency and different system states, possibly leading to suboptimal scheduling decisions. This work introduces IconqSched, a new, principled non-intrusive scheduler that optimizes the execution order and timing of queries to enhance total end-to-end runtime as experienced by the user query queuing time plus system runtime. Unlike previous approaches, IconqSched features a novel fine-grained predictor, Iconq, which treats the DBMS as a black box and accurately estimates the system runtime of concurrently executed queries under different system states. Using these predictions, IconqSched is able to capture system runtime variations across different query mixes and system loads. It then employs a greedy scheduling algorithm to effectively determine which queries to submit and when to submit them. We compare IconqSched to other schedulers in terms of end-to-end runtime using real workload traces. On Postgres, IconqSched reduces end-to-end runtime by 16.2%-28.2% on average and 33.6%-38.9% in the tail. Similarly, on Redshift, it reduces end-to-end runtime by 10.3%-14.1% on average and 14.9%-22.2% in the tail.

Problem

• Non-intrusive Query Scheduling
• Query Optimization
• System Load

Innovation

• Non-intrusive Scheduler
• Iconq Technology
• Query Latency Reduction