Distributed Load Balancing Health Check via Service Node Intermediaries

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The existing distributed load balancing systems face inefficiencies due to the large quantity of detection messages sent by virtual load balancers to access nodes, which not only affect other services but also increase signaling load, leading to suboptimal performance.

Innovation Solution

A cloud management platform is introduced to manage the distributed load balancing system, where it determines the status of backend servers by sending check request messages to service nodes, which then utilize detection modules to share the status with virtual load balancers, reducing the number of detection messages and signaling load by using a centralized approach.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the virtual load balancer sends detection messages to each target backend server to obtain server status, then the health check function is achieved, but the signaling load on access nodes and the quantity of detection messages increase significantly

Engineering Contradiction:
Improvehealth check accuracyVSAvoidquantity of detection messages
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The patent introduces service nodes as intermediaries between access nodes and backend servers. Service nodes collect health check information from multiple backend servers and forward aggregated results to access nodes, reducing the number of direct detection messages from access nodes to individual backend servers while maintaining comprehensive health monitoring coverage.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent combines multiple health check functions into a unified service node architecture. Instead of having each access node independently check each backend server, the service node consolidates health check operations, aggregates results, and provides unified status information to multiple access nodes, thereby reducing redundant detection messages.

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If the virtual load balancer sends detection messages to each target backend server, then the status of backend servers is monitored, but the signaling load on access nodes increases

Engineering Contradiction:
Improveserver status monitoringVSAvoidsignaling load
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

Service nodes act as intermediaries that consolidate health check signaling. They receive status information from multiple backend servers and forward aggregated results to access nodes, significantly reducing the signaling load on access nodes while maintaining comprehensive server status monitoring.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the health check function into two parts: service nodes perform detailed status collection from backend servers, while access nodes receive aggregated results for load balancing decisions. This segmentation reduces the signaling burden on access nodes while preserving monitoring reliability.

Inventive Principle:
Principle #1Segmentation

3Reliability

If a large quantity of detection messages are sent in the distributed load balancing system, then comprehensive health check coverage is achieved, but other services in the system are affected

Engineering Contradiction:
Improvehealth check coverageVSAvoidinterference with other services
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

Service nodes serve as intermediaries that handle all health check communications with backend servers, isolating the detection message traffic from other services. Access nodes only receive aggregated health status results, not raw detection messages, thereby preventing interference with other system services while maintaining comprehensive health check coverage.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3361675B1Distributed load balancing system, health check method and service node
Publication Date: 2019.05.08 HUAWEI TECH CO LTD
  • EP3361675B1 patent drawingFigure 1
  • EP3361675B1 patent drawingFigure 2
  • EP3361675B1 patent drawingFigure 3

AI summary

Embodiments of the present invention pertain to the field of cloud network technologies, and disclose a distributed load balancing system, a health check method, and a service node. The distributed load balancing system includes a cloud management platform, an access node, and at least one service node, where the access node and the at least one service node are physical servers, a first virtual load balancer runs on the access node, and at least one backend server runs on the service node. A detection message is sent by using a detection module on a target service node to detect a status of a target backend server, and the status of the target backend server is shared to a first load balancer by using the detection module. Therefore, not only a quantity of detection messages in the load balancing system is reduced, but also signaling load on the access node is reduced. The detection module is deployed in a first namespace on the target service node, and the first virtual load balancer is deployed in a second namespace on the access node, where the first namespace and the second namespace have a same IP address, thereby reducing IP address resources.