TOR Switch Link Detection via Out-of-Band Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In data centers, failures in the network link between Top of Rack (TOR) switches and servers can cause service interruptions, leading to economic losses due to the lack of effective fault detection and monitoring mechanisms.
Innovation Solution
A link detecting method and system that uses out-of-band communication via a network-management switch to acquire and analyze connection relationships between TOR switches and servers, enabling timely fault detection, diagnosis, and prevention of service interruptions by periodically sending query messages and keep-alive messages to determine the state of connections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If out-of-band communication via network-management switch is used for link detection, then link fault detection capability is improved, but system complexity increases due to additional communication paths and protocols
Solution Approach 1:
The patent introduces a network-management switch as an intermediary component that establishes an out-of-band communication channel independent of the service link between TOR switch and server. This mediator enables fault detection by allowing the server to query link status through the network-management switch without relying on the potentially failed service link, thus resolving the contradiction between improved detection capability and system complexity.
2Reliability
If periodic query messages and keep-alive messages are sent for link monitoring, then real-time fault detection is improved, but network bandwidth consumption increases
Solution Approach 1:
The patent implements periodic query messages sent at configured intervals to check link status, combined with keep-alive messages that use minimal bandwidth to maintain connection liveness. This periodic action approach provides real-time fault detection capability while controlling bandwidth consumption by using efficient message formats and configurable polling intervals, rather than continuous monitoring.
Solution Approach 2:
The patent extracts link detection functionality from the service data plane and places it in the out-of-band management plane. By separating detection traffic from service traffic, the system can monitor link health without consuming service bandwidth, resolving the contradiction between real-time detection and bandwidth consumption.
3Reliability
If connection relationships between TOR switch and servers are continuously monitored, then service interruption prevention is improved, but processing overhead increases
Solution Approach 1:
The patent establishes connection relationships between TOR switch service interfaces and server service interfaces in advance through the server-side program before service interruptions can occur. By pre-configuring and storing these relationships, the system can quickly detect faults without real-time processing overhead during normal operation, enabling rapid response when failures occur.
Solution Approach 2:
The patent implements a feedback mechanism where the server-side program periodically queries link status through the network-management switch and compares current status with expected connections. This feedback loop enables automatic detection of service interruptions and triggers alerts or corrective actions, preventing prolonged service disruptions while maintaining efficient processing through event-driven updates rather than continuous monitoring.
Data Source
AI summary
A link detection method includes: a server-side program acquiring connection relationships between a service interface of a TOR switch and service interfaces of various servers; the server-side program periodically sending a query message to each client-side program by means of a network management switch; in response to the query message, each client-side program returning, to the server-side program and by means of the network management switch, interface information of a service interface, which is included in a TOR switch or a server at which each client-side program is located and has connection relationships with service interfaces of other devices; and the server-side program reporting, to an upper-layer program, interface information of a service interfaces of the other devices, and the received interface information, such that the upper-layer program analyzes, on the basis of the interface information, connection situation of links for realizing corresponding connection relationships.