Network Processor Pipeline Design for Unknown L2 Addressing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing solutions for network traffic flooding are ineffective due to antiquated processing pipeline designs in previous generation network processors, which fail to efficiently handle data-link layer addressing resolutions, leading to unknown destinations in network traffic transmission.

Innovation Solution

The implementation of advanced network processors with updated processing pipeline designs that include ingress and egress processing pipelines, crossbar fabrics, and data structures for L2 and L3 lookups, enabling the network device to flood network traffic across identified network broadcast domains and determine the correct physical network interfaces for destination transmission.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If existing network processors with antiquated processing pipeline designs are used, then device complexity is reduced, but network traffic forwarding efficiency deteriorates and unknown destination handling fails

Engineering Contradiction:
Improvenetwork traffic forwarding efficiencyVSAvoidprocessing pipeline design complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The network processor is divided into distinct ingress and egress processing pipelines, each handling specific forwarding tasks. The ingress pipeline performs lookups and forwarding decisions, while the egress pipeline handles packet transmission, allowing parallel processing and improved efficiency without requiring a complete redesign of the entire system.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension to the processing pipeline by adding hierarchical lookup capabilities (L2 and L3 lookups) and multiple forwarding table dimensions. This allows the system to handle unknown destinations by searching through multiple layers of forwarding information, transforming a single-dimension lookup problem into a multi-dimensional solution space.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If advanced processing pipelines with L2 and L3 lookups are implemented, then network traffic flooding capability is improved, but device complexity increases

Engineering Contradiction:
Improveunknown destination handling capabilityVSAvoiddata structure complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The forwarding tables and data structures are designed to serve multiple functions simultaneously. The same lookup mechanisms are used for both known and unknown destination scenarios, and the forwarding tables store information that supports both unicast and broadcast/multicast forwarding operations, reducing the need for separate specialized structures.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system performs preliminary lookups in the ingress pipeline to determine forwarding decisions before packets are fully processed. By pre-computing forwarding information and storing it in optimized data structures, the system prepares handling paths for both known and unknown destinations in advance, reducing complexity during actual packet processing.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If network traffic flooding is implemented for unknown mappings, then delivery reliability is improved, but network bandwidth consumption increases

Engineering Contradiction:
Improvetraffic delivery reliabilityVSAvoidnetwork bandwidth consumption
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

Instead of flooding all network traffic to unknown destinations, the system performs partial flooding by first attempting targeted lookups in the forwarding tables. Only when these lookups fail does the system resort to flooding operations, and even then, it limits flooding to necessary broadcast domains or VLANs, reducing unnecessary bandwidth consumption while maintaining delivery reliability.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system implements feedback mechanisms where flooding operations are monitored and adjusted based on learned traffic patterns and destination information. When destinations become known through learning or manual configuration, the system switches from flooding to targeted unicast forwarding, dynamically optimizing bandwidth usage while ensuring reliable delivery.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11824738B2Network traffic flooding for unknown data-link to transport mapping scenarios
Publication Date: 2023.11.21 ARISTA NETWORKS INC
  • US11824738B2 patent drawing
  • US11824738B2 patent drawing
  • US11824738B2 patent drawing

AI summary

A method and network device for network traffic flooding. Specifically, the method and network device disclosed herein implement the mitigation of the lack of data-link layer (or L2) addressing resolutions, usually learned by or programmed manually into the network device, through the flooding of affected network traffic across identified network broadcast domains. Flooding of the network traffic in the aforementioned manner may ensure that at least the destination(s) of the network traffic receives the network traffic at least in scenarios where which it is unknown out of which particular physical network interface(s) should the network traffic be transmitted to reach the destination(s).