Link Stability Management via Dual-Source Health Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Link failures between computers in data centers are often misdiagnosed due to reliance solely on networking device perspectives, leading to incorrect error reporting and potential performance impacts.
Innovation Solution
Implementing a management module that monitors link health by retrieving statistics from both the adapter and networking device, determining health acceptability, and instructing corrective actions via out-of-band data communications to maintain link stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If link health monitoring relies solely on networking device statistics, then the monitoring system is simple, but link failure diagnosis is inaccurate
Solution Approach 1:
The patent segments the link health monitoring function into two independent monitoring paths: one at the networking device (switch) and one at the adapter. Each side independently collects its own statistics and reports to the management module, enabling comprehensive diagnosis without requiring one system to monitor the other directly.
Solution Approach 2:
The management module acts as an intermediary that receives statistics from both the networking device and the adapter, compares them, and determines link health status. This mediator consolidates information from multiple sources to achieve accurate diagnosis while keeping the monitoring systems themselves relatively simple.
2Reliability
If the management module monitors link health from both adapter and networking device perspectives, then link failure diagnosis accuracy improves, but system complexity increases
Solution Approach 1:
The management module performs multiple functions: it collects statistics from both adapter and networking device, monitors link health, compares statistics, and triggers corrective actions. This multi-functional approach consolidates complexity into a single dedicated module rather than distributing it across multiple components.
Solution Approach 2:
The system implements feedback loops where the management module continuously receives statistics from both sides, compares current state with expected state, and triggers corrective actions when discrepancies are detected. This feedback mechanism maintains link stability through automated response to detected issues.
3Reliability
If corrective actions are executed based on comprehensive link statistics, then link stability improves, but response time may increase
Solution Approach 1:
The system pre-configures corrective actions in the management module based on common link failure patterns. When specific statistical patterns are detected, pre-determined corrective actions are immediately executed without requiring complex real-time analysis, reducing response time while maintaining reliability.
Solution Approach 2:
The monitoring and corrective action system operates dynamically, adjusting its behavior based on the specific statistics received. The management module can adaptively choose different corrective actions based on the nature of the detected issue, optimizing the balance between thoroughness and speed.
Data Source
AI summary
Managing stability of a link coupling an adapter of a computing system to a port of a networking device for in-band data communications, the adapter and the network device coupled for out-of-band data communications to a management module, where link stability is managed by: monitoring link health including retrieving adapter link statistics from the adapter and networking device link statistics from the networking device; determining, in dependence upon the adapter and networking device link statistics, whether the link health meets predefined health acceptability criteria; and if the link health does not meet predefined health acceptability criteria, instructing the adapter to execute one or more predefined corrective actions.