Multi-Node Fan Control Switch With Watchdog Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional server systems face inefficiencies and reliability issues in fan control schemes, which can lead to interruptions due to excessive heat and potential security breaches or revenue losses, as they rely on a single chassis manager controller for temperature monitoring and fan speed control.
Innovation Solution
Implementing a multi-node fan control switch system where each node has a controller with a watchdog circuit that monitors the health of the specific controller and enables an external mode if it fails, allowing a neighboring node's controller to take over cooling fan management, thereby providing redundant and efficient fan speed control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single chassis manager controller is used to control fan speeds, then the device complexity is reduced, but the reliability of fan control deteriorates
Solution Approach 1:
The patent implements local quality by giving each node its own fan control capabilities through local fan control circuits and temperature sensors, rather than relying on a single centralized controller. This allows each node to independently monitor its own temperature and control its own fans, improving reliability while maintaining simplicity at the local level.
Solution Approach 2:
The patent applies preliminary action by implementing a watchdog circuit that continuously monitors the health status of the node controller before failures occur. When the watchdog detects controller malfunction, it automatically triggers the fan control switch to transition to external control mode, ensuring continuous fan operation without interruption.
2Reliability
If a multi-node fan control system with redundancy is implemented, then the reliability of fan control is improved, but the device complexity increases
Solution Approach 1:
The patent implements universality by designing the fan control switch to have multiple functions: it can operate in internal control mode when the node controller is healthy, and automatically switch to external control mode when the node controller fails. This multi-functional design provides redundancy and improved reliability without requiring completely separate control systems.
Solution Approach 2:
The patent merges the fan control functionality at the node level by integrating fan control circuits, temperature sensors, and watchdog circuits directly into each node. This consolidation allows the node to self-monitor and self-control its cooling fans, reducing the need for complex centralized control while improving reliability through distributed control.
3Reliability
If continuous monitoring of controller health is implemented, then the reliability of fan control during failures is improved, but the use of energy increases
Solution Approach 1:
The patent applies self-service by implementing a watchdog circuit that autonomously monitors the health status of the node controller and automatically triggers the fan control switch to transition between internal and external control modes without requiring additional energy-intensive external monitoring systems. The watchdog circuit uses minimal energy to continuously check controller status and initiate failover when needed.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
Various examples of the present disclosure provide a multi-node fan control switch and systems and methods for controlling one or more cooling fans of a node using a fan control switch and a specific controller (e.g., BMC or a specific processor) of the node. The node also includes a watch dog circuit. The watch dog circuit can monitor health of the specific controller and, in response to determining that the specific controller has failed, enable the fan control switch to an external mode to allow a controller of a neighboring node in the rack system to control the one or more cooling fans of the node.