Distributed Proxy Server Workload Management for QoS Assurance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Centralized workload management in hierarchical network systems is complex, scalable, and prone to failure, while distributed management lacks service differentiation and QoS assurance, struggling to meet diverse resource requirements and workload characteristics in cloud environments.

Innovation Solution

A distributed workload management system with a proxy server that periodically determines dispatch rates for service levels based on measured request-related information and service quality parameters, using a utility function to allocate rates and ensure service differentiation and fairness, and an application server that calculates and distributes a maximum admitted rate for resource management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If centralized workload management is adopted, then QoS assurance and service differentiation are improved, but system complexity and implementation overhead increase

Engineering Contradiction:

ImproveQoS assuranceVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent divides the centralized workload management system into distributed components across multiple proxy servers. Each proxy server independently performs rate control and request dispatching based on local service level configurations, eliminating the need for a complex centralized controller while maintaining QoS assurance through distributed decision-making

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system enables proxy servers to autonomously manage their own workload dispatching without requiring centralized control. Each proxy server self-configures rate controllers and request dispatchers based on service level agreements, reducing implementation complexity while maintaining reliable QoS through decentralized self-management

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If distributed workload management is adopted, then system scalability and fault tolerance are improved, but service differentiation and QoS assurance deteriorate

Engineering Contradiction:

Improvesystem scalabilityVSAvoidservice differentiation

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies local quality by configuring each proxy server with service level-specific parameters and policies tailored to different service levels. This allows distributed proxy servers to maintain service differentiation capabilities locally while preserving system scalability through independent configuration of each node

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system pre-configures service level agreements and rate control parameters on each proxy server before runtime. This preliminary configuration enables distributed proxy servers to immediately provide service differentiation without requiring complex real-time centralized coordination, thus maintaining both scalability and QoS assurance

Inventive Principle:

Principle #10Preliminary action

3Ease of operation

If centralized controller is used, then workload management decisions are centralized, but system overhead and implementation time increase

Engineering Contradiction:

Improvecentralized controlVSAvoidimplementation time

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The patent copies the rate control and request dispatching logic from a hypothetical centralized controller to multiple distributed proxy servers. Each proxy server maintains a local copy of the workload management functionality, eliminating implementation delays associated with centralized control while preserving ease of operation through standardized configurations

Inventive Principle:

Principle #26Copying

4Productivity

If centralized management unit is used, then traffic flow is centralized, but fault tolerance and system resilience decrease

Engineering Contradiction:

Improvetraffic management efficiencyVSAvoidfault tolerance

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent segments the centralized traffic management function into independent distributed components across multiple proxy servers. This segmentation maintains traffic management efficiency through localized decision-making while improving fault tolerance by eliminating single points of failure inherent in centralized architectures

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS9712448B2Proxy server, hierarchical network system, and distributed workload management method

Publication Date: 2017.07.18 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A proxy server and a hierarchical network system and a distributed workload management method. According to one embodiment of this disclosure, the proxy server includes: a rate controller configured to, based on measured request-related information and service quality parameters relative to service levels of requests, periodically determine a dispatch rate for requests of each service level, wherein the sum of the dispatch rate for respective service levels is less than or equal to a predetermined rate; and a request dispatcher configured to dispatch the requests of the corresponding service level in accordance with the dispatch rate determined by the rate controller. One aspect of the disclosure realizes a low overhead, highly scalable, simple and efficient workload management system to achieve QoS assurance and overload protection.