Non-disruptive Route Change in Fibre Channel Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fibre channel networks experience congestion and reduced throughput due to data transmission disruptions when switching routes, leading to slower communication and inefficiencies.
Innovation Solution
Implementing a non-disruptive route change method within fibre channel networks using a transmission controller that continuously monitors network traffic and switches data communication routes without pausing data transmission, utilizing exchange-based routing and coordinated data packet transmission systems to optimize traffic flow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If route switching is performed in traditional fibre channel networks, then network congestion can be alleviated, but data transmission disruption occurs resulting in frame drops and reduced throughput
Solution Approach 1:
The patent establishes a bidirectional forwarding relationship between port pairs in advance, before congestion occurs. When congestion is detected on a route, the system can immediately switch to an alternative pre-established route without disruption. This preliminary setup of multiple forwarding paths enables seamless route switching while maintaining continuous data transmission, thus improving throughput without sacrificing reliability.
Solution Approach 2:
The patent introduces a fabric identifier and exchange identifier as intermediaries to manage multiple routes. These identifiers enable the system to track and manage different data flows through different routes, allowing congestion-aware routing decisions to be made without disrupting ongoing transmissions. The intermediary mechanisms facilitate smooth transitions between routes by maintaining context information.
2Productivity
If congestion control protocols are implemented, then network traffic can be managed, but CPU utilization increases reducing overall system efficiency
Solution Approach 1:
The patent implements a self-service congestion control mechanism where switches autonomously monitor their own buffer occupancy and make routing decisions based on local conditions. Each switch independently identifies congested routes and selects alternative paths using pre-established bidirectional forwarding relationships, without requiring centralized control or intensive CPU processing. This distributed self-service approach maintains effective traffic management while minimizing CPU utilization.
Solution Approach 2:
The patent changes the monitoring parameter from complex traffic analysis to simple buffer occupancy thresholds. By tracking whether buffer occupancy exceeds a predetermined threshold, the system achieves effective congestion detection with minimal processing requirements. This parameter simplification allows switches to make rapid routing decisions without heavy CPU involvement, maintaining traffic management efficiency while reducing energy consumption.
3Adaptability or versatility
If route changes are performed during data transmission, then network optimization can be achieved, but frame drops occur disrupting communication
Solution Approach 1:
The patent pre-establishes bidirectional forwarding relationships between port pairs before data transmission begins. When route changes are needed due to congestion, the system switches to an alternative pre-configured route that already has the necessary forwarding relationships in place. This eliminates the need to establish new routes during transmission, preventing frame drops and ensuring continuous accurate data delivery while maintaining adaptability to network conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A system and method for non-disruptive route change. The method includes receiving a first data transmission frame associated with a first exchange at a switch, transmitting the first data transmission frame through a first route based on a route lookup, determining, by a traffic optimization circuit, an improved second route, determining if the first exchange includes any other data transmission frames, and transmitting a first data transmission frame associated with a second exchange through the second route in response to determining that the first exchange does not include any other data transmission frames.