ECMP Path Group Switching to Reduce Network Failover Delay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high path switching delay in network devices with equal cost multipath (ECMP) is caused by the extensive modifications required in the routing and forwarding tables during active-standby path switching, leading to inefficient network performance.
Innovation Solution
Implement a method where the network device maintains an ECMP table with path group identifiers that are updated based on availability, allowing only the path group identifiers to be changed from valid to invalid when all paths in the active group fail, thereby reducing the need for extensive table updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the network device updates the routing and forwarding table content during active-standby path switching, then the path switching can be completed, but the path switching delay increases due to the extensive modifications required
Solution Approach 1:
The patent segments the path information into two separate tables: an ECMP table that stores path group identifiers and a next-hop (NHP) table that stores detailed path information. During path switching, only the ECMP table needs to be updated with a new path group identifier, while the NHP table remains unchanged. This segmentation allows for minimal table updates and significantly reduces path switching delay.
Solution Approach 2:
The patent pre-establishes multiple path groups (active and standby) and pre-configures their identifiers in the ECMP table before any failure occurs. When a path failure is detected, the system simply switches to a pre-configured standby path group by updating the ECMP table identifier, rather than computing and configuring new paths in real-time. This preliminary preparation eliminates the need for extensive real-time table modifications.
2Loss of information
If the network device maintains detailed routing and forwarding tables with all path information, then complete path information is available, but the table update complexity and time consumption increase
Solution Approach 1:
The patent divides path information storage into two segments: the ECMP table stores only path group identifiers (ECMP indices) that provide a high-level view of available paths, while the NHP table stores the complete detailed path information. This segmentation allows the system to maintain complete path information while simplifying update operations, as only the compact ECMP table needs to be modified during path switching.
Solution Approach 2:
The patent creates a simplified copy of path information in the ECMP table that contains only essential identification data (ECMP indices) rather than complete path details. This copy allows for rapid updates and comparisons during path switching operations, while the original detailed path information remains intact in the NHP table for when it is actually needed.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This application provides a path switching method and a related apparatus. In the path switching process, an ECMP table includes a first ECMP index of a first path group and a second ECMP index of a second path group; when all paths in the first path group have failed, a path group identifier corresponding to the first ECMP index may be changed from valid to invalid in the ECMP table, indicating that all paths in the first path group are unavailable. In this case, a path group identifier corresponding to the second ECMP index is valid, indicating that the second path group includes an available path, thereby completing switching between an active path and a standby path. In this process, only an identifier corresponding to the ECMP index needs to be updated, and therefore, the time consumed is relatively short, and the path switching delay can be effectively reduced.