Software RAID Crash Dump Controller Routing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing information handling systems face challenges in providing effective crash dump functionality for software RAID systems, particularly when dealing with spanned and non-spanned logical storage subsystems, as conventional crash dump operations fail to access secondary controller devices.

Innovation Solution

A direct-attached storage device software RAID system that presents a single primary controller device to the hypervisor subsystem, receives crash dump commands, and transmits these commands to a subset of physical storage devices via respective controller devices, ensuring access to all necessary storage devices for crash dump operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single primary controller device is presented to the hypervisor subsystem for simplified system architecture, then device complexity is reduced, but crash dump operations cannot access secondary controller devices

Engineering Contradiction:
Improvecontroller device presentationVSAvoidcrash dump operation
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The software RAID subsystem acts as an intermediary between the hypervisor subsystem and multiple controller devices. It receives crash dump commands from the hypervisor and intelligently routes them to the appropriate controller devices (primary or secondary) based on the logical storage subsystem configuration, enabling comprehensive crash dump functionality while maintaining simplified system architecture.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If conventional crash dump commands are sent only through the primary controller device, then system operation is simplified, but crash dump operations fail for spanned logical storage subsystems that require access to secondary controller devices

Engineering Contradiction:
Improvecrash dump command transmissionVSAvoidcrash dump operation completeness
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system dynamically determines the appropriate controller device for crash dump operations based on the logical storage subsystem configuration. For non-spanned subsystems, commands are sent through the primary controller device. For spanned subsystems, the software RAID subsystem automatically routes commands through secondary controller devices, providing adaptive and reliable crash dump functionality.

Inventive Principle:
Principle #15Dynamics

3Reliability

If hardware-based RAID data protection solution is implemented, then data protection reliability is improved, but device cost increases significantly

Engineering Contradiction:
Improvedata protectionVSAvoidhardware RAID controller
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces hardware-based RAID controllers with a software RAID subsystem that runs on the host system. This software-based approach provides equivalent RAID functionality (including crash dump operations) without requiring expensive dedicated hardware controllers, reducing system cost while maintaining data protection reliability.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250036314A1Direct-attached storage device software raid crash dump system
Publication Date: 2025.01.30 DELL PROD LP
  • US20250036314A1 patent drawing
  • US20250036314A1 patent drawing
  • US20250036314A1 patent drawing

AI summary

A direct-attached storage device software RAID crash dump system includes a chassis housing a software RAID subsystem coupled to physical storage devices, controller devices, and a hypervisor subsystem. The software RAID subsystem presents a primary controller device to the hypervisor subsystem as being connected to a logical storage device provided by the physical storage devices. When the software RAID subsystem receives a first crash dump command from the hypervisor subsystem directed to the primary controller device and identifying a crash dump logical storage subsystem in the logical storage device, it transmits a respective second crash dump command to each of a subset of the physical storage devices that provide the crash dump logical storage subsystem via a respective controller device that couple the software RAID subsystem to that physical storage device, confirms completion of the respective second crash dump commands, and transmits a crash dump confirmation to the hypervisor subsystem.