Dynamic Partitioning for Distributed Data Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Database systems face challenges in efficiently managing large data sets across multiple node devices due to unpredictable resource availability, leading to inefficiencies in data organization and processing.

Innovation Solution

A dynamic partitioning approach is implemented, where data set subportions are organized and processed based on resource availability, with the ability to interrupt and dispatch subportions when resource limits are reached, and process them in parallel across node devices, allowing for flexible organization and continuation of tasks across threads.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If data set subportions are organized and processed in a distributed parallel environment, then processing efficiency and productivity are improved, but resource management complexity and device complexity increase due to unpredictable resource availability

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidresource management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent implements dynamic partitioning where the data set is divided into multiple subportions that can be dynamically allocated and reorganized based on real-time resource availability. The system monitors resource status and adjusts the distribution of data subportions across node devices, allowing flexible adaptation to changing resource conditions while maintaining high processing efficiency

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The data set is segmented into multiple manageable subportions that can be independently processed by different node devices. This segmentation enables parallel processing and allows the system to distribute workloads more effectively across available resources, improving overall productivity while reducing the complexity of managing large datasets

Inventive Principle:
Principle #1Segmentation

2Productivity

If data organization and processing tasks are executed continuously, then productivity is improved, but reliability decreases when resource availability becomes insufficient

Engineering Contradiction:
Improveprocessing throughputVSAvoidtask completion reliability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms that continuously monitor resource availability and task progress. When resource constraints are detected, the system adjusts its behavior by pausing, reorganizing, or redistributing data subportions to ensure reliable completion of processing tasks while maintaining high productivity during periods of sufficient resource availability

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary organization and preparation of data subportions before actual processing begins. By pre-organizing data and anticipating resource constraints, the system can better manage task execution and ensure reliable completion even when resource availability fluctuates during processing

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If dynamic partitioning and reorganization of data subportions is implemented, then adaptability to resource constraints is improved, but device complexity and programming complexity increase

Engineering Contradiction:
Improveadaptability to resource constraintsVSAvoidprogramming complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements self-service mechanisms where node devices automatically monitor their own resource availability and participate in the dynamic partitioning process without requiring complex external control. Each device autonomously adjusts its data processing tasks based on local resource conditions, reducing programming complexity while maintaining high adaptability to resource constraints

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS9298807B1Techniques for dynamic partitioning in a distributed parallel computational environment
Publication Date: 2016.03.29 SAS INSTITUTE INC
  • US9298807B1 patent drawing
  • US9298807B1 patent drawing
  • US9298807B1 patent drawing

AI summary

An apparatus includes an organization component to retrieve from task instructions an indication of a type of organization of data set subportions prior to performance of a computation and a data item by which the data set subportions are to be organized, organize the data set subportion among others based on the data item and type of organization, monitor availability of a first processing resource and a first storage resource of a node device employed to organize the data set subportions, and based on insufficient availability of at least one of the first processing resource or the first storage resource, interrupt the organization of the data set subportions, and dispatch a first set of one or more organized data set subportions to be processed; and a performance component to execute the task instructions to process the organized data set subportion.