BMC Redundant Communication Path via External Network Switch

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Communication failures between Baseboard Management Controllers (BMCs) and the server rack chassis controller in information handling systems can lead to significant performance degradation and unreliable recovery processes due to unreliable communication protocols and physical connection failures.

Innovation Solution

A redundant communication path is established using a network switch external to the server rack chassis, allowing BMCs to communicate with the chassis controller through another BMC, ensuring continuous communication and recovery even in case of internal connection failures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If BMCs are communicatively connected to the chassis controller internal to the server rack, then communication speed and reliability are improved, but the system is vulnerable to physical connection failures within the rack

Engineering Contradiction:
Improvecommunication reliabilityVSAvoidcommunication path complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces a network switch as an intermediary device external to the server rack chassis. This network switch mediates communication between BMCs and the chassis controller, providing an alternative communication path that bypasses internal rack connections. When internal connections fail, BMCs can communicate through the network switch, thereby improving reliability without significantly increasing system complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If a redundant communication path through another BMC and network switch is established, then communication reliability is improved, but communication latency and complexity increase

Engineering Contradiction:
Improvecommunication redundancyVSAvoidcommunication latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent implements dynamic path selection where the system automatically chooses between direct internal communication paths and redundant external paths through the network switch. When the direct path is available, it is used for low-latency communication. When failures are detected, the system dynamically switches to the redundant path, balancing reliability needs with latency concerns.

Inventive Principle:
Principle #15Dynamics

3Reliability

If BMCs communicate through the network switch external to the server rack, then resistance to internal connection failures is improved, but network dependency increases

Engineering Contradiction:
Improvefailure resistanceVSAvoidnetwork infrastructure dependency
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent makes the network switch a universal communication endpoint that serves multiple functions: it acts as a backup communication path for BMCs, provides network access for management purposes, and enables external monitoring and control capabilities. This multi-functionality justifies the added network infrastructure by providing multiple benefits beyond just redundancy.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10728086B2System and method for providing a redundant communication path between a server rack controller and one or more server controllers
Publication Date: 2020.07.28 DELL PROD LP
  • US10728086B2 patent drawing
  • US10728086B2 patent drawing
  • US10728086B2 patent drawing

AI summary

A server rack may include a chassis controller for the server rack and a set of baseboard management controllers (BMCs) corresponding to servers stored in the server rack. Each BMC is communicatively connected to the chassis controller internal to the server rack. Each BMC is also communicatively connected to a network switch located external to the server rack to communicate with the set of BMCs using the network switch. When a first BMC loses communication with the chassis controller internal to the server rack, the first BMC communicates with the chassis controller via a second BMC and the network switch.