Cut-Through Network Fabric Link Error Source Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In cut-through forwarding network fabrics, identifying the source of link errors is challenging due to the latency reduction mechanism, which makes it difficult to determine the actual location of network errors as multiple devices may register errors, leading to a time-consuming and inefficient troubleshooting process.

Innovation Solution

Automatically detecting link errors by polling network devices multiple times to collect error statistics, tracing the errors upstream until reaching a device that does not use cut-through forwarding or lacks increasing error rates, thereby identifying the source network link as the last traversed link.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If cut-through forwarding is implemented to reduce packet transmission latency, then the forwarding speed is improved, but the ability to identify the actual source of network errors deteriorates

Engineering Contradiction:
Improvepacket forwarding speedVSAvoiderror source identification difficulty
Core Design Contradiction:
SpeedVSDifficulty of detecting and measuring

Solution Approach 1:

The patent introduces an intermediary system consisting of monitoring devices and error tracking mechanisms that mediate between the cut-through forwarding process and error detection. This intermediary layer tracks error propagation through the network fabric without interfering with the high-speed forwarding, allowing identification of the actual error source while maintaining latency reduction benefits

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent implements feedback mechanisms where error information is collected from multiple network devices and fed back to a central analysis system. This feedback loop enables the system to trace errors back to their source by analyzing which devices registered errors and correlating this with traffic flow patterns, thus solving the identification problem while preserving cut-through forwarding performance

Inventive Principle:
Principle #23Feedback

2Reliability

If multiple network devices register link errors in a cut-through forwarding fabric, then error detection coverage is improved, but the time required to identify the actual error source increases

Engineering Contradiction:
Improveerror detection coverageVSAvoidtroubleshooting time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the error analysis process into distinct phases: error collection at multiple devices, error correlation analysis, and source identification. By dividing the troubleshooting process into manageable segments and automating each phase, the system maintains comprehensive error detection coverage while significantly reducing the time required to identify the actual error source

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by pre-configuring error tracking at all network devices and establishing error correlation rules before errors occur. This preparation allows the system to immediately begin analyzing errors when they occur, eliminating the need for manual investigation and reducing troubleshooting time while maintaining comprehensive detection

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10129184B1Detecting the source of link errors in a cut-through forwarding network fabric
Publication Date: 2018.11.13 AMAZON TECH INC
  • US10129184B1 patent drawing
  • US10129184B1 patent drawing
  • US10129184B1 patent drawing

AI summary

Techniques and solutions are provided for detecting the source of link errors in a cut-through forwarding network fabric. For example, a network link that is the source of the link errors can be automatically located by polling a network device a number of times to identify a network interface that has an increasing error rate and tracing network interface error rates back through one or more upstream network devices to locate the network link that is the source of the link errors.