Analytics Node Detects SAN Oversubscription via Mirror Frames
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network management systems face challenges in accurately detecting oversubscription and measuring latency in storage area networks (SANs), leading to performance and stability issues due to complex data processing and multiple flows competing for bandwidth, which can result in poor response times and input/output failures.
Innovation Solution
An analytics and diagnostic node monitors fabric networks in real-time by receiving mirror command frames from switches to determine latency metrics and data rates, calculating average data rates, and flagging oversubscription when the cumulative data rate exceeds a threshold, thereby identifying device and fabric failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple devices transmit data over a single link in a SAN, then network resource utilization improves, but oversubscription occurs causing performance degradation and stability issues
Solution Approach 1:
The patent applies preliminary action by proactively detecting oversubscription conditions before they cause severe performance degradation. The system continuously monitors data rates and latency metrics, and preemptively identifies when cumulative data rates approach link capacity thresholds, allowing administrators to take corrective action before stability issues occur.
Solution Approach 2:
The patent implements feedback mechanisms by continuously monitoring data rates, latency metrics, and oversubscription conditions, then using this information to dynamically adjust network management decisions. The system provides real-time feedback about link utilization and oversubscription status to enable adaptive resource allocation and prevent performance degradation.
2Measurement precision
If real-time monitoring of multiple flows is implemented, then oversubscription detection accuracy improves, but system complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the monitoring task into discrete components: individual flow monitoring, aggregation of data rates, separate latency measurement, and distinct oversubscription detection logic. This modular approach allows precise monitoring of multiple flows while managing system complexity through structured organization of monitoring functions.
Solution Approach 2:
The patent uses an intermediary approach by introducing a dedicated monitoring entity that collects data from multiple flows and processes oversubscription detection centrally. This intermediary component aggregates information from various sources, standardizes measurements, and provides a unified view of network conditions, simplifying the overall monitoring architecture.
3Measurement precision
If cumulative data rate calculation is performed for all flows, then oversubscription detection accuracy improves, but processing overhead increases
Solution Approach 1:
The patent applies partial action by calculating cumulative data rates selectively rather than continuously for all flows at maximum precision. The system monitors flows and aggregates their data rates, but can adjust the granularity and frequency of calculations based on network conditions, performing sufficient monitoring to detect oversubscription while avoiding unnecessary processing overhead.
Data Source
AI summary
An analytics and diagnostic node according to the present disclosure monitors oversubscription and determines flow metrics by receiving mirror command frames from one or more switching nodes. The mirror command frames could correspond to a multiple flows traversing over a connection within a network. The analytics and diagnostic node collects at least one latency metric for each of the flows using timestamps found within the mirror command frames. Based on the latency metrics and timestamps, the analytic diagnostic node determines an average data rate for each of the flows. The analytics and diagnostic node also computes the cumulative data rates corresponding to different bucket intervals based on the average data rates. To detect oversubscription, the analytics and diagnostic node compares the cumulative data rates with one or more oversubscription rules.