PCIe Root Complex Mirroring Block for Data Redundancy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Information handling systems face challenges in maintaining data redundancy and recovery during failures of PCIe adaptors and ports, as existing solutions do not effectively manage differences in configuration and redundancy across multiple servers and virtual machines.
Innovation Solution
The implementation of a PCIe root complex with a mirroring block that creates redundancy by mirroring data from a primary PCIe adaptor to a secondary adaptor, allowing for data recovery and adaptation in case of failures, using PCIe configuration information to manage different link sizes and storage capacities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is striped across multiple drives using RAID, then data redundancy is improved, but the solution does not effectively manage differences in configuration and redundancy across multiple servers and virtual machines
Solution Approach 1:
The patent segments the storage system into multiple hierarchical levels: individual physical drives, virtual disk groups, virtual machine storage allocations, and server-level configurations. This segmentation allows each layer to be managed independently with appropriate redundancy strategies, resolving the contradiction by enabling both RAID-style redundancy and flexible configuration management across different virtualization layers.
Solution Approach 2:
The virtualization layer provides universal redundancy management that works across multiple servers, virtual machines, and storage configurations. A single virtual disk can be accessed by multiple virtual machines while maintaining redundancy, and the same infrastructure supports both striped and mirrored configurations dynamically, achieving both reliability and adaptability.
2Reliability
If a single drive fails, then the remaining drives can be used to recreate the lost data, but existing solutions do not effectively manage differences in configuration and redundancy across multiple servers and virtual machines
Solution Approach 1:
The patent introduces a virtualization layer as an intermediary between physical storage devices and virtual machines. This intermediary abstracts the complexity of redundancy management by handling drive failures, data reconstruction, and configuration differences at the virtualization layer, rather than requiring complex management at each server or virtual machine level. The virtualization layer mediates between the physical RAID infrastructure and the logical storage requirements of multiple virtual machines.
3Reliability
If data is mirrored from primary PCIe adaptor to secondary adaptor, then data retention during failures is improved, but system complexity increases
Solution Approach 1:
The patent implements preliminary mirroring actions where data is proactively copied from primary PCIe adaptors to secondary adaptors before failures occur. This preliminary action ensures that redundant copies are already in place and can be immediately activated upon failure, improving data retention while managing complexity through automated, pre-configured redundancy rather than reactive complexity.
Solution Approach 2:
The patent uses data copying to create redundant instances of storage data across multiple PCIe adaptors. By maintaining copies of data on secondary adaptors that can be quickly activated, the system achieves high reliability for data retention. The copying mechanism is managed through virtualization software that abstracts the complexity, presenting a simple interface while handling the underlying complexity of multiple adaptor configurations.
Data Source
AI summary
An information handling system includes a peripheral component interconnect express root complex, a basic input output system, and a root complex mirroring block. The peripheral component interconnect express root complex includes a plurality of peripheral component interconnect express ports. The basic input output system is in communication with the peripheral component interconnect express root complex, and is configured to detect a peripheral component interconnect express adaptor configuration, and to set a peripheral component interconnect express mirroring setting based on the peripheral component interconnect express adaptor configuration. The root complex mirroring block is in communication with the basic input output system, and is configured to mirror data between a first peripheral component interconnect express adaptor and a second peripheral component interconnect express adaptor based on the peripheral component interconnect express mirroring setting.