Watchdog Module for Server Graceful Shutdown During Power Loss
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computing systems face challenges in ensuring graceful shutdown during power failures, particularly when the baseboard management controller (BMC) is unresponsive or undergoing updates, leading to potential data loss from volatile memory.
Innovation Solution
A system comprising a power supply unit (PSU), a battery, and a computer system with a management controller and watchdog module, where the watchdog module initiates a timer to ensure graceful shutdown upon detecting a PSU issue, aborting the timer if the management controller responds, and providing backup power to allow time for data transfer before battery depletion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If BMC software is used to manage graceful shutdown, then shutdown control functionality is provided, but reliability deteriorates due to software bugs, updates, and unresponsive states
Solution Approach 1:
A watchdog timer is introduced as an intermediary mechanism between the power failure event and the shutdown execution. The watchdog timer independently monitors whether the BMC responds within a specified timeframe and autonomously triggers shutdown if the BMC fails to respond, thereby mediating the unreliable BMC software and ensuring shutdown reliability.
Solution Approach 2:
The watchdog timer is pre-configured with a timeout threshold before power failure occurs. Upon detecting power failure, it immediately starts counting and automatically triggers shutdown if the BMC does not respond within the predetermined time, performing the shutdown action in advance before complete power loss.
2Reliability
If BMC handles power failure gracefully, then data integrity is maintained, but response time increases due to software processing delays
Solution Approach 1:
The watchdog timer implements a feedback mechanism by monitoring whether the BMC has responded to the power failure event within the expected timeframe. If no response is detected (negative feedback), the watchdog timer automatically triggers shutdown, ensuring timely data preservation without excessive delays.
3Duration of action of moving object
If battery backup is provided, then shutdown time is extended, but energy consumption increases
Solution Approach 1:
The battery backup provides only the minimal necessary energy to keep critical components running for the watchdog timer's timeout period (typically seconds to minutes), rather than providing full backup power for extended operation. This partial action approach extends shutdown time just enough to ensure data integrity while minimizing battery energy consumption.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enhances the likelihood of graceful server shutdown and data preservation during power outages by ensuring timely shutdown even if the management controller is unresponsive, thereby increasing operational reliability and data integrity.
Implementation Method 1
The battery provides the specified direct current (DC) voltage to provide backup power to components connected to the direct current output when problems providing the direct current output from the power supply unit (PSU) occur
Data Source
Figure 1
Figure 2
AI summary
Aspects extend to methods, systems, and computer program products for remediating power loss at a server. Aspects of the invention increase the likelihood of gracefully shutting down a server and associated components in a data center when mains power is lost for a specified amount of time (e.g., an amount of time beyond transition to generator power). A server can include a management module (e.g., a BMC) and a watchdog module. When the management controller detects loss of power at a power supply unit, the management controller orchestrates a graceful shutdown of the server in response to power loss. When the management module is unresponsive, the watchdog module provides backup functionality for orchestrating a graceful shutdown in response to power loss. As such, data can be saved from RAM to more durable storage even when the management module is unresponsive.