Fault-Tolerant Memory Fabric Failure Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems with fault-tolerant mechanisms, such as RAID and end-to-end retransmission schemes, face challenges in preventing silent data corruption when multiple redundancy controllers enter degraded mode due to independent fabric device failures, leading to unsynchronized operations and potential data inconsistencies.
Innovation Solution
Implementing a method where redundancy controllers periodically test routes and determine failures, allowing them to distinguish between media controller failures and fabric device failures, thereby synchronizing entry into degraded mode and preventing silent data corruption by using protocol-layer interactions and end-to-end retransmission sequences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If redundancy controllers independently enter degraded mode due to fabric device failures, then fault tolerance is maintained, but silent data corruption occurs due to unsynchronized operations
Solution Approach 1:
The patent implements a feedback mechanism where redundancy controllers exchange status information and coordinate their entry into degraded mode. Controllers monitor each other's state and only transition to degraded mode when certain conditions are met, ensuring synchronization. This feedback loop prevents silent data corruption by ensuring all controllers are in the same state before accessing redundant data.
Solution Approach 2:
Before entering degraded mode, redundancy controllers perform preliminary actions by testing routes and determining the cause of fabric device failures. They exchange information about the failure conditions and coordinate their transition to degraded mode accordingly. This preliminary coordination ensures that all controllers agree on the system state before accessing redundant data, preventing data corruption.
2Measurement precision
If redundancy controllers continuously monitor routes to detect failures, then failure detection accuracy is improved, but system complexity and overhead increase
Solution Approach 1:
The patent implements periodic route testing rather than continuous monitoring. Redundancy controllers test routes at scheduled intervals to detect fabric device failures. This periodic action provides sufficient failure detection accuracy while significantly reducing the complexity and overhead associated with constant monitoring. The timing and frequency of these periodic tests are optimized to balance detection accuracy with system resource consumption.
3Adaptability or versatility
If multiple redundancy controllers operate independently, then system scalability is improved, but coordinated failure detection becomes difficult
Solution Approach 1:
The patent segments the failure detection function into individual controller actions while maintaining overall coordination. Each redundancy controller independently tests its own routes and determines local failure conditions, but they use standardized protocols to exchange status information. This segmentation allows system scalability while maintaining coordinated failure detection through structured communication between controllers.
Solution Approach 2:
The patent uses parameter changes in the form of standardized status indicators and failure condition thresholds. Controllers monitor specific parameters (route status, response times) and transition between defined states (normal, degraded, failed). This parameter-based approach enables independent operation while facilitating coordinated failure detection through clear, standardized state representations that all controllers understand.
Data Source
AI summary
According to an example, a failed component in a fault-tolerant memory fabric may be determined by transmitting request packets along a plurality of routes between the redundancy controller and a media controller in periodic cycles. The redundancy controller may determine whether route failures for all of the plurality of routes have occurred within a number of consecutive periodic cycles. In response to determining that route failures for all of the plurality of routes have occurred within a number of consecutive periodic cycles, the media controller is established as failed. In response to determining that route failures for less than all of the plurality of routes have occurred within the number of consecutive periodic cycles, a fabric device is established as failed.