Service Processor Traps for Storage Controller Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage networks face challenges in quickly and reliably detecting storage controller failures across clusters, leading to disruptive client access due to reliance on slow or imprecise techniques like timeouts and manual switchover, especially in single-controller configurations without local high availability pairs.
Innovation Solution
Implementing service processor traps that allow for rapid communication between service processors in different storage clusters, enabling automatic switchover operations by exchanging communication configurations and using service processor traps to initiate failover access without network connectivity reliance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If timeouts and manual switchover techniques are used for cross-cluster storage controller failure detection, then system complexity is reduced, but failure detection speed and reliability deteriorate
Solution Approach 1:
The patent introduces service processors as intermediary components that actively monitor storage controller health and send trap notifications to remote clusters. This intermediary mechanism enables reliable and fast failure detection without requiring complex distributed monitoring infrastructure, resolving the contradiction by providing a simple yet effective notification pathway.
Solution Approach 2:
The patent implements a feedback mechanism where service processors continuously monitor storage controller status and immediately notify remote clusters upon detecting failures. This real-time feedback loop enables rapid automatic switchover operations, improving failure detection reliability while maintaining system simplicity through dedicated monitoring components.
2Ease of manufacture
If single storage controller configurations are used without local high availability pairs, then cost is reduced, but client access disruption increases during failures
Solution Approach 1:
The patent implements preliminary action by pre-configuring remote disaster recovery clusters with service processors that are ready to receive failure notifications and initiate switchover operations immediately upon detecting controller failures. This pre-prepared state enables rapid response without requiring expensive local high availability pairs, reducing both cost and downtime.
Solution Approach 2:
The patent replaces the mechanical approach of local high availability pairing with a remote notification-based system. Instead of requiring physical proximity and complex local failover mechanisms, the system uses electronic trap notifications and automated remote switchover, achieving similar reliability at lower cost.
3Reliability
If automatic switchover operations are implemented through service processor traps, then client access continuity is improved, but device complexity increases
Solution Approach 1:
The patent implements self-service by enabling storage controllers and service processors to automatically detect failures and initiate switchover operations without human intervention. The service processors autonomously monitor controller health, send trap notifications, and trigger failover sequences, improving client access continuity while managing complexity through automated self-managing components.
Data Source
AI summary
One or more techniques and/or computing devices are provided for communicating storage controller failures utilizing service processor traps. A first storage controller, of a first storage cluster, has a disaster recovery relationship with a second storage controller of a second storage cluster. The first storage controller comprise a first service processor configured to monitor health of the first storage controller. Responsive to identifying a failure of the first storage controller, the first service processor uses stored communication configuration of a second service processor of the second storage controller to send a service processor trap to the second service processor. In this way, the second service processor initiates a switchover operation by the second storage controller to provide clients with failover access to data previously available through the first storage controller before the failure. Proactive notification of storage controller failures utilizing service processor traps reduces client data access disruptions.