Relational Database Operator Fusion to Reduce Recursive Processing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Relational databases face performance issues and reduced hardware resource utilization due to recursive invocation of multiple operators, which cannot be fundamentally addressed by horizontal hardware expansion.

Innovation Solution

Implementing a data processing method that determines an acceleration policy for operation commands, utilizing a bypass framework to combine operators and dynamically access target partitions, and optimizing transaction log writing to reduce recursive invocations and resource competition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If horizontal expansion of hardware resources is used to improve processing performance, then computing and storage resources are increased, but hardware resource utilization is reduced

Engineering Contradiction:

Improveprocessing performanceVSAvoidhardware resource utilization

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The patent combines multiple operators into a fused operator that performs multiple operations in a single execution unit. This merging eliminates the need for separate hardware resources for each operator, improving resource utilization while maintaining processing performance through optimized operation fusion

Inventive Principle:

Principle #5Merging (Combining)

2Productivity

If multiple operators are used to implement operations on relational database, then processing capability is enhanced, but recursive invocation increases processing duration

Engineering Contradiction:

Improveprocessing capabilityVSAvoidprocessing duration

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

Multiple operators are merged into a single fused operator that executes multiple operations atomically. This eliminates recursive invocations and reduces processing duration while maintaining the enhanced processing capability through operation fusion and reduced overhead

Inventive Principle:

Principle #5Merging (Combining)

3Adaptability or versatility

If multiple operators perform recursive invocation to complete operations, then processing flexibility is improved, but hardware resource occupation increases

Engineering Contradiction:

Improveprocessing flexibilityVSAvoidhardware resource occupation

Core Design Contradiction:

Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The fused operator combines multiple operations into a single execution unit that maintains processing flexibility through configurable operation sequences while reducing hardware resource occupation by eliminating redundant operator instances and their associated overhead

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS12380075B2Data processing method and apparatus, and computing system

Publication Date: 2025.08.05 HUAWEI TECH CO LTD

AI summary

In accordance with an embodiment, a data processing method includes: obtaining a first operation command, where the first operation command is used to perform data processing in a relational database; determining an acceleration policy of the first operation command, wherein the acceleration policy is used to accelerate a processing process of the first operation command; and performing an operation of the first operation command based on the acceleration policy.