Boot Processor Role Switching for Loss of Lockstep Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems face challenges in detecting and responding to loss of lockstep (LOL) in multi-processor systems without crashing the system, especially in large systems prone to frequent cosmic events, and existing solutions are either OS-centric or require significant processor and platform-specific knowledge, leading to inefficiencies and potential crashes.
Innovation Solution
A method that detects loss of lockstep in a multi-processor system, determines if the affected processor is the boot processor, and switches the role of the boot processor to a spare processor without shutting down the operating system, using system firmware to manage the transition and maintain system availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system crashes to prevent data corruption propagation upon loss of lockstep, then data integrity is improved, but system availability deteriorates
Solution Approach 1:
The patent creates a copy of the boot processor's state in a spare processor before the actual failure occurs. When loss of lockstep is detected, the spare processor (containing the copied state) takes over as the new boot processor, allowing continuous operation without crash. This copying mechanism enables fault tolerance while maintaining system availability.
Solution Approach 2:
The system performs preliminary action by pre-configuring a spare processor and copying the boot processor's state to it before any failure occurs. This advance preparation ensures that when loss of lockstep is detected, the transition to the spare processor can happen immediately without requiring system crash or reboot, thus maintaining both data integrity and availability.
2Productivity
If the system switches boot processor role to maintain availability, then system availability is improved, but system complexity increases
Solution Approach 1:
The spare processor serves multiple functions: it acts as a standby backup, a state copy destination, and a ready-to-takeover boot processor. This multi-functionality reduces the need for separate dedicated components and simplifies the overall system architecture while maintaining high availability.
Solution Approach 2:
The system performs self-service by automatically detecting loss of lockstep, identifying the spare processor, copying the boot processor state, and switching roles without external intervention. This automated self-recovery mechanism reduces operational complexity while ensuring continuous system operation.
3Reliability
If lockstep monitoring is implemented to detect errors, then data integrity is improved, but processing overhead increases
Solution Approach 1:
The patent extracts the error detection function from continuous processing by using lockstep monitoring that only actively compares operations when discrepancies arise. The spare processor mechanism handles the heavy lifting of state management and recovery, reducing the processing overhead required for maintaining integrity during normal operation.
Data Source
AI summary
According to one embodiment, a method comprises detecting loss of lockstep (LOL) for a processor in a multi-processor system. The method further comprises determining that the processor for which the LOL is detected is assigned the role of boot processor, and switching the role of boot processor to a spare processor without shutting down the system's operating system. In another embodiment, a method comprises system firmware determining that an LOL is detected for a lockstep pair of processors that are assigned the role of boot processor in a system. The method further comprises determining one of the lockstep pair of processors that is not the cause of the LOL, and copying the state of the determined one of the lockstep pair of processors that is not the cause of the LOL to a spare processor. The method further comprises switching the role of boot processor to the spare processor.