External PCIe Links for Online Node-Pair Enclosure Replacement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In storage arrays, replacing an enclosure with a failed midplane requires taking both nodes housed in the enclosure offline due to internal PCIe links, which is undesirable in high availability environments.
Innovation Solution
Implement external PCIe links between storage nodes to enable communication independence from the enclosure, allowing for online enclosure replacement by using temporary and new enclosures with synchronized data mirroring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If internal PCIe links are used within the enclosure, then device complexity is reduced, but system availability deteriorates during enclosure replacement
Solution Approach 1:
The system segments the communication path by providing dual interconnect options: internal PCIe links through the midplane and external PCIe links independent of the enclosure. This segmentation allows nodes to communicate through external links when the enclosure is replaced, maintaining system availability while preserving the simple internal enclosure structure.
Solution Approach 2:
External PCIe interconnects act as intermediaries between storage nodes, providing an alternative communication path that bypasses the enclosure's internal midplane. This intermediary connection enables enclosure replacement without taking nodes offline, resolving the contradiction between simple enclosure design and high system availability.
2Reliability
If external PCIe links are implemented, then system availability is maintained during enclosure replacement, but device complexity increases
Solution Approach 1:
The system dynamically adapts its communication path based on enclosure status. Nodes can switch between internal PCIe links (when enclosure is functional) and external PCIe links (when enclosure replacement is needed), providing dynamic flexibility that maintains availability while managing complexity only when necessary.
Solution Approach 2:
The system changes the communication parameter from exclusively internal PCIe links to a configurable dual-path mode. By adjusting the interconnect parameter between internal and external modes, the system maintains simplicity during normal operation and introduces external links only when availability is required during enclosure replacement.
3Reliability
If all nodes are taken offline for enclosure replacement, then data integrity is ensured through synchronization, but loss of time occurs
Solution Approach 1:
The system performs preliminary data synchronization and mirroring between nodes before enclosure replacement. This preliminary action ensures data integrity is already established, allowing the replacement to proceed without requiring nodes to be taken offline for synchronization, thereby eliminating downtime while maintaining data integrity.
Solution Approach 2:
External PCIe links enable continuous communication between storage nodes during enclosure replacement. This continuity of useful action allows data synchronization to occur without interruption, maintaining both data integrity and system availability simultaneously by preventing downtime.
Data Source
AI summary
Methods and apparatuses for online replacement of a node enclosure are provided. A storage array system includes a node-pair housed in a node enclosure. Each node of the node-pair are be linked to a network and further linked to each other by external interconnects, independent of the enclosure. The interconnects couple the first storage node to the second storage node externally of the node enclosure. The node-pairs are configured to communicate independently of the node enclosure and the enclosure is replaceable without disruption of communication over the network.