White-Box Micro-Adaptive Query Processing

Operator performance in in-memory data management systems (DMS) often suffers from micro-architectural hazards such as cache misses and branch mispredictions. While many operators have alternative implementations that are robust against such hazards, these generally perform worse when no hazards are...

Full description

Saved in:
Bibliographic Details
Published in:Data engineering pp. 2880 - 2893
Main Authors: Pearce, Jack, Mohr-Daurat, Hubert, Pirk, Holger
Format: Conference Proceeding
Language:English
Published: IEEE 19.05.2025
Subjects:
Engines
Glass box
Hazards
in-memory database
Measurement
micro-adaptivity
micro-architectural hazards
Microarchitecture
Monitoring
Optimization
Pathology
Query processing
Runtime
white-box optimization
ISSN:2375-026X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Operator performance in in-memory data management systems (DMS) often suffers from micro-architectural hazards such as cache misses and branch mispredictions. While many operators have alternative implementations that are robust against such hazards, these generally perform worse when no hazards are encountered. Unfortunately, hazards are caused by order-dependent data characteristics that query optimizers struggle to capture (e.g., sortedness, clusteredness) making a priori hazard-conscious optimization difficult. Additionally, statically optimized plans fail to adapt when data characteristics vary within a table. To address these problems, we propose a hazardadaptive approach to query execution. Through hardwareassisted runtime profiling of low-level metrics, operators dynamically adapt to "hazardous" data. We propose an architecture for hazard-adaptive operators and integrate our approach into a DMS. We demonstrate that using hazard-adaptive operators provides a \sim \mathbf{2-20} \times speedup across several TPC-H queries.
ISSN:2375-026X
DOI:10.1109/ICDE65448.2025.00216