Hierarchical Cluster Network Loop Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Resilient Packet Ring (RPR) networks face issues with looping, which degrades performance and causes message duplication due to multiple active paths between rings, and existing solutions like spanning tree protocols are slow in reconfiguring network topology after a fault.
Innovation Solution
Implementing a hierarchical cluster structure with a parent cluster broadcasting messages on all interconnects and child clusters divided into subclusters, each associated with an interconnect, to prevent looping and ensure rapid recovery by limiting message propagation through specific interconnects and using filters to control communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple interconnects are used between RPR clusters to avoid single point of failure, then network reliability is improved, but looping occurs causing message duplication and performance degradation
Solution Approach 1:
The network is segmented into parent clusters and child clusters with hierarchical relationships. Each child cluster is divided into subclusters that are associated with specific interconnects. This segmentation allows messages to be routed through specific hierarchical paths, preventing loops while maintaining multiple interconnects for reliability.
Solution Approach 2:
The patent introduces an interconnect association mechanism as an intermediary layer between clusters and subclusters. Each subcluster is associated with a specific interconnect, acting as a mediator that controls message flow and prevents unauthorized routing that could create loops, while still allowing redundant paths for reliability.
2Object-generated harmful factors
If spanning tree protocol is used to prevent looping, then looping is prevented, but reconfiguration time after fault is slow
Solution Approach 1:
The patent establishes hierarchical cluster structures and interconnect associations in advance before faults occur. Parent clusters and child clusters are pre-configured with their relationships and associated interconnects, so when a fault occurs, the pre-established hierarchy enables rapid reconfiguration without needing slow spanning tree calculations.
Solution Approach 2:
The hierarchical structure allows dynamic reconfiguration based on fault conditions. When an interconnect fails, the pre-established hierarchy enables rapid switching to alternative paths through associated subclusters, providing dynamic adaptation much faster than traditional spanning tree protocols.
3Area of stationary object
If all interconnects are used for broadcasting messages, then network coverage is improved, but looping and bandwidth duplication occur
Solution Approach 1:
The patent applies local quality by associating specific subclusters with specific interconnects. Instead of uniformly broadcasting to all interconnects, messages are selectively routed through interconnects associated with relevant subclusters, providing targeted coverage while avoiding unnecessary bandwidth consumption on unrelated paths.
Data Source
AI summary
Methods and apparatus for eliminating loops associated with interconnects between clusters are disclosed. According to one aspect of the present invention, a method for operating a cluster of an interconnect group that includes at least one node and is in communication with a plurality of interconnects includes broadcasting a first frame on the interconnects. The method also includes receiving a second frame, the second frame being received on only a first interconnect, and blocking the second frame from being broadcast on the first interconnect. Finally, the method includes broadcasting the received second frame throughout the cluster such that no node in the cluster receives more than one copy of the second frame.