Service Processor Forensics via NC-SI During Storage Controller Failure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In a cluster environment, when a storage controller fails, administrators face challenges in obtaining forensics to diagnose the failure since communication with the service processor is routed through the storage controller, making remote access unavailable.
Innovation Solution
Configuring service processors to collect and expose forensics directly to a cluster health monitor using alternative communication paths, such as the Network Controller Sideband Interface (NC-SI), even during storage controller failures, ensuring continuous access for diagnostic purposes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If communication with the service processor is routed through the storage controller, then the service processor can be managed and monitored, but remote access becomes unavailable when the storage controller fails
Solution Approach 1:
The patent introduces a cluster health monitor as an intermediary component that can directly access the service processor through alternative communication paths (such as the NC-SI interface) when the storage controller fails. This mediator enables continuous monitoring and forensics collection without relying on the failed storage controller, resolving the contradiction between maintaining service processor availability and preserving remote access capability.
2Stability of the object's composition
If the service processor operates independent of the storage controller, then it can continue functioning during storage controller failure, but communication paths become unavailable
Solution Approach 1:
The patent adds another communication dimension by implementing alternative communication paths (such as the Network Controller Sideband Interface or NC-SI) that are independent of the storage controller. This allows the service processor to maintain operational independence while preserving forensics accessibility through a different communication channel, effectively adding a dimensional alternative to the failed communication path.
3Difficulty of detecting and measuring
If administrators want to obtain forensics during storage controller failure, then diagnostic capability is needed, but communication through the failed controller is unavailable
Solution Approach 1:
The cluster health monitor serves as a mediator that can directly communicate with the service processor through alternative paths to collect forensics during storage controller failures. This intermediary approach enables failure diagnosis capability while maintaining communication availability, as the health monitor can access the service processor without relying on the failed storage controller.
Data Source
AI summary
One or more techniques and/or systems are provided for collecting forensics associated with a failure of a storage controller. For example, a storage node, of a cluster environment, may comprise a service processor and a storage controller. The storage controller may manage a storage device accessible, through the storage controller, to one or more client devices. The service processor may manage the storage controller (e.g., collect operational statistics of the storage controller, perform software and/or firmware updates for the storage controller, etc.). The service processor may obtain forensics associated with a failure of the storage controller, and may provide the forensics to a cluster health monitor notwithstanding the storage controller being in an inoperable state (e.g., the service processor may send the forensics through a network interface controller of the storage node, over a non-client storage management network, to the cluster health monitor).