BMC Multi-Path Call Home for Server Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Baseboard management controllers (BMCs) often face challenges in reliably sending error information to a call home destination due to management server failures in datacenters, leading to incomplete or unsuccessful transmission of critical error messages.
Innovation Solution
An intelligent multi-path call home method is implemented, where the BMC detects errors and attempts to send call home messages to a management server, and if the message is not successfully relayed, it independently transmits the message to the destination through alternative paths, such as proxies or routers, ensuring delivery even if the management server fails.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the BMC sends call home messages through the management server, then the message transmission follows a standardized centralized path, but the transmission may fail when the management server is unavailable
Solution Approach 1:
The communication path is segmented into multiple independent routes: a primary path through the management server and alternative direct paths from BMC to call home destination. This segmentation allows the system to switch between paths based on availability, improving reliability without requiring complex dynamic routing logic in the BMC itself.
Solution Approach 2:
The management server acts as an intermediary in the primary communication path, providing centralized control and standardization. Meanwhile, alternative paths bypass this intermediary directly, allowing messages to reach the destination even when the server is unavailable. This dual approach maintains the benefits of centralized management while ensuring delivery reliability.
2Reliability
If the BMC implements multiple transmission paths, then the fault tolerance improves, but the system complexity increases
Solution Approach 1:
Alternative call home destinations and transmission paths are pre-configured in the BMC before failures occur. When the primary management server path fails, the BMC can immediately switch to a pre-configured alternative path without requiring complex real-time decision-making or dynamic path discovery, thus improving fault tolerance while minimizing added complexity.
Solution Approach 2:
The system changes the transmission parameter from a single fixed destination through the management server to multiple configurable destinations with different path configurations. This allows the BMC to adapt to failure conditions by changing which destination parameter is active, providing fault tolerance through parameter variability rather than complex structural changes.
3Reliability
If the BMC independently transmits messages to the call home destination, then the message delivery succeeds despite management server failures, but the loss of centralized control increases
Solution Approach 1:
The BMC is equipped with the capability to independently transmit call home messages directly to alternative destinations without requiring management server intervention. This self-service capability ensures message delivery reliability while maintaining centralized control over the configuration of alternative paths and destinations, balancing autonomy with manageability.
Solution Approach 2:
The BMC is designed with multi-functionality, capable of operating in both managed mode (through the management server) and autonomous mode (direct transmission to alternative destinations). This universality allows the system to maintain centralized control when the server is available while independently ensuring message delivery when the server fails, without requiring separate systems for each mode.
Data Source
AI summary
A method for an intelligent multi-path call home includes detecting, at a BMC, an error in a computing device managed by the BMC and sending a call home message to a management server. The computing device is one of a plurality of computing devices each with a BMC in communication with the management server. The management server is programmed to relay the call home message to a call home destination remote from the computing devices and management server. The method includes determining that the management server failed to receive the call home message and/or failed to successfully relay the call home message to the call home destination, and transmitting, from the BMC, the call home message to the call home destination in response to determining that the management server failed to receive the call home message and/or failed to successfully relay the call home message to the call home destination.