Storage Network Congestion Detection and Impact Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional congestion-detecting methodologies in storage area networks (SANs) are inadequate in identifying the cause of congestion and its impact on the network, leading to inefficiencies and performance issues.
Innovation Solution
The system collects configuration and performance data to identify congested switch ports, determine the impact of congestion, and estimate the reason for congestion by analyzing telemetry data, including congestion ratios and error rates, and triggering alerts for mitigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional congestion-detecting methodologies are used, then congestion can be detected, but the cause and impact of congestion cannot be identified
Solution Approach 1:
The patent segments the congestion analysis into multiple dimensions: (1) detecting congestion at switch ports, (2) analyzing upstream ports and ISLs to identify congestion sources, and (3) determining downstream impact. This segmentation allows the system to not only detect congestion but also identify its causes and impacts by examining different parts of the network topology separately and systematically.
Solution Approach 2:
The patent introduces an intermediary analysis layer that examines inter-switch links (ISLs) and upstream ports as mediators between the congested port and potential congestion sources. By analyzing the ISL utilization and upstream port status, the system can infer congestion causes without directly observing the root cause device, thus preserving information that would otherwise be lost.
2Productivity
If no congestion analysis is performed, then system complexity is low, but network performance issues cannot be resolved
Solution Approach 1:
The patent implements self-service by enabling the network monitoring system to automatically detect congestion, analyze its causes through upstream port and ISL examination, determine downstream impact, and generate alerts without human intervention. This automated self-diagnosis capability improves network productivity by resolving performance issues faster while keeping the system complexity manageable through standardized analysis procedures.
Solution Approach 2:
The patent establishes feedback loops where congestion detection triggers automated analysis of upstream ports and ISLs, which then feeds back information about congestion causes. This feedback mechanism continuously monitors network status and adjusts alerts based on analyzed data, improving network response to performance issues while maintaining controlled complexity through systematic feedback processing.
3Loss of information
If detailed congestion analysis is implemented, then congestion causes and impacts can be identified, but detection and measurement difficulty increases
Solution Approach 1:
The patent applies preliminary action by pre-establishing the network topology map, including all switch ports, inter-switch links (ISLs), and their relationships before congestion occurs. When congestion is detected, the system can immediately query pre-identified upstream ports and ISLs without needing to dynamically discover the topology, thus reducing detection difficulty while maintaining detailed analysis capability.
Solution Approach 2:
The patent simplifies detection by changing parameters to standardized metrics such as ISL utilization thresholds and port status indicators. Instead of analyzing complex raw data, the system monitors specific parameters like congestion ratios and error rates, making detection and measurement easier while still providing detailed information about congestion causes and impacts through these standardized parameters.
Data Source
AI summary
Techniques for determining an impact that a congested switch port is having on a network and for estimating a reason as to why the congested switch port is congested are disclosed. Configuration data and performance data from a network are obtained. Based on the configuration data, a shortest path between a storage port and a host port is identified. A particular switch port is also identified as a result of that port being congested. An impact as to how the switch port, due to its congestion in the particular shortest path, is impacting or is being impacted by other switch ports in the network is determined. An alert, which includes information indicating the impact, is triggered.