Tunnel-Less SD-WAN Forwarding Without Per-Packet Header Replacement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing SD-WAN systems require encapsulating each packet with tunnel headers at every node, leading to inefficiencies due to the need for header removal and replacement, which is resource-intensive and inefficient.
Innovation Solution
A tunnel-less SD-WAN system where the ingress node identifies the path and sends a prepended set of SD-WAN header values for the first packet, which is used to create records at each hop to forward subsequent packets, eliminating the need for repeated header encapsulation and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If encapsulation headers are added to each packet at every node, then packet routing through SD-WAN is enabled, but processing overhead and resource consumption increase
Solution Approach 1:
The ingress node performs preliminary routing setup by creating forwarding state and identifying the complete path before packets arrive. This preliminary action eliminates the need for per-packet header manipulation at intermediate nodes, as the routing decisions are pre-computed and cached in forwarding tables.
Solution Approach 2:
The patent extracts the routing intelligence from individual packet headers and concentrates it in separate forwarding tables at each node. Instead of embedding next-hop information in every packet header, the routing logic is extracted into node-local forwarding state that is established once per flow and reused for all packets in that flow.
2Productivity
If tunnel headers are removed and replaced at each successive node, then packet forwarding is achieved, but processing time and resource usage increase
Solution Approach 1:
Forwarding tables are pre-populated with next-hop information before packet arrival. This preliminary setup allows intermediate nodes to forward packets using simple table lookups rather than performing time-consuming header removal, analysis, and reconstruction operations for each packet.
Solution Approach 2:
The patent uses forwarding tables that contain pre-computed routing information copied from the ingress node's path identification. Instead of re-analyzing packet headers at each node, the routing decisions are copied into local forwarding state that can be quickly consulted for rapid packet forwarding.
3Productivity
If path identification is performed at the ingress node for the entire flow, then routing is established, but scalability and flexibility decrease
Solution Approach 1:
The patent segments the routing function across multiple nodes. The ingress node performs initial path identification and creates forwarding state, but each intermediate node maintains independence by using its own forwarding table. This segmentation allows each node to operate autonomously while contributing to the overall routing function, improving both efficiency and flexibility.
Solution Approach 2:
The forwarding tables at each node are dynamically populated based on flow characteristics and network conditions. This dynamic setup allows the system to adapt to different traffic patterns and network states while maintaining the efficiency benefits of pre-computed routing information for active flows.
Data Source
AI summary
In a novel tunnel-less SD-WAN, when an ingress node of the SD-WAN receives a new packet flow, it identifies the path of the flow through the SD-WAN, and sends an initial prepended set of SD-WAN header values before the first packet for the flow to the next hop along this identified path, rather than encapsulating each packet of the flow with encapsulating tunnel headers that store SD-WAN next hop data for the flow. The prepended set of SD-WAN header values are then used to not only forward the first packet through the SD-WAN, but also to create records at each subsequent hop, which are then used to forward subsequent packets of the flow through the SD-WAN.