Dual Controller Disk Array Automatic Path Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current dual controller disk arrays require complex configurations and additional software to switch data paths when a controller node fails, leading to increased redundancy and costs.
Innovation Solution
The dual controller disk array design allows controller nodes to detect each other's validity and automatically switch data paths without pre-configured redundant paths or multi-path software, enabling seamless failover without the need for additional software installation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multi-path software is installed in the server to switch data paths when a controller node fails, then the system can achieve failover capability, but the device complexity and configuration complexity increase significantly
Solution Approach 1:
The controller nodes automatically detect each other's status and perform path switching without requiring multi-path software or manual configuration on the server. The system serves itself by having controller nodes monitor each other's health and autonomously redirect data paths when a failure is detected, eliminating the need for complex external software solutions
Solution Approach 2:
The controller nodes act as intermediaries that monitor each other's status and coordinate failover automatically. Instead of requiring the server to manage path switching through complex software, the controller nodes themselves become the mediators that detect failures and redirect data flows between each other
2Reliability
If redundant data paths are pre-configured for failover, then the system can switch paths when a controller node is invalid, but the quantity of data and configuration overhead increases
Solution Approach 1:
The controller nodes perform preliminary mutual detection and status monitoring before failures occur. By continuously checking each other's health status in advance, the system can immediately activate failover when needed without requiring pre-configured redundant data paths or additional software, thus avoiding the accumulation of redundant data
Solution Approach 2:
Each controller node is designed to be multi-functional, capable of both processing its own data and taking over the peer node's data when needed. This universal design allows the system to achieve failover capability without requiring dedicated redundant paths, as either controller can handle data from either source
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The present invention discloses a disk array, which is applied to a storage system including the dual controller disk array and a server. The disk array includes a disk frame and two controller nodes. Each controller node includes a switch, where a port of the switch is connected to a port of a switch of a peer controller node. Each controller node is configured to detect whether the peer controller node is invalid through the port. When it has been detected that the peer controller node is invalid, a local controller node enables the peer controller node to send, through the port of the switch of the peer controller node, received data sent by the server to a port of a switch of the local controller node.