Active Link Verification for Storage Network Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated failover strategies in storage networks can unnecessarily switch to an alternate path even if the primary path is still operational at a lower physical level, leading to interruptions in system drivers and software applications, and require manual reconfiguration in adaptive infrastructures.
Innovation Solution
Implementing active link verification using low-level protocol packets, or 'heartbeat' commands and responses, between local and remote fabric devices to determine the operational status of storage device paths, allowing for intelligent failover decisions without interrupting physical connections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If host-to-target communication is used to verify path availability, then automated failover can be implemented, but unnecessary failovers occur when linking devices are inoperative at higher communication levels while the physical path remains intact
Solution Approach 1:
The patent introduces an intermediary verification mechanism that checks the operational status of linking devices (switches, routers, fabric devices) between the host and storage target. This intermediary layer provides accurate information about actual path availability, preventing false failover decisions when higher-level communication issues occur but physical connectivity remains intact.
Solution Approach 2:
The patent replaces the software-level host-to-target communication mechanism with a physical/link-level verification mechanism. Instead of relying on high-level protocol responses that can be blocked by software issues, the system uses lower-level link status detection to determine actual path availability, substituting a more reliable detection method.
2Extent of automation
If host-to-target communication is used for path verification, then automated failover is enabled, but system drivers and software applications are interrupted
Solution Approach 1:
The patent uses an intermediary verification layer that operates independently of host software applications and system drivers. By checking path availability through fabric devices or link-level protocols rather than through host software, the system obtains accurate path status information without interrupting or being affected by host software operations.
Solution Approach 2:
The patent segments the failover verification process into separate layers: physical link status verification is performed independently from host software operations. This segmentation allows the system to determine path availability through fabric device status without requiring host software to be active, thereby avoiding software interruptions while maintaining automated failover capability.
3Ease of operation
If manual reconfiguration is used for failover, then user control is maintained, but time-consuming operations and user expertise requirements increase
Solution Approach 1:
The patent enables the storage system to perform self-verification of path availability using link-level status information from fabric devices. This self-service capability allows the system to automatically determine when failover is necessary without requiring user intervention, thereby reducing failover time while maintaining operational simplicity.
Data Source
AI summary
Systems and methods for active link verification for failover operations in a storage network are disclosed. An exemplary method includes issuing a command from a first port of a storage device to a local network device in the storage network. The method also includes receiving a response to the command at the first port of the storage device from the local network device in the storage network. The storage device fails over to a second port of the storage device if no response is received at the first port of the storage device.