Active-Active Failover for Direct-Attached Storage Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage solutions, such as centralized data storage systems and Storage Area Networks (SANs), are costly and complex, while Direct Attached Storage (DAS) lacks fault tolerance, making it unsuitable for smaller enterprises that require cost-effective redundant storage systems.
Innovation Solution
Implementing an active-active failover capability in DAS systems using a port expander and storage controllers to enable one DAS server to take over storage services from another in case of failure, with zoning features to manage storage zones and ensure seamless failover and failback processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If DAS systems are used, then cost is reduced, but fault tolerance is lost
Solution Approach 1:
The storage system is segmented into multiple independent DAS servers, each with its own storage controller and storage devices. The port expander divides the storage pool into multiple zones that can be independently assigned to different servers. This segmentation allows individual servers to fail without affecting the entire storage system, providing fault tolerance while maintaining the cost-effectiveness of DAS architecture.
Solution Approach 2:
The system dynamically changes the zoning parameters of the port expander to reconfigure storage device assignments when failover occurs. By modifying the zone configuration parameters, the system can rapidly redirect storage access from a failed server to a surviving server without physical reconfiguration, enabling cost-effective fault tolerance through software-controlled parameter changes.
2Reliability
If SAN-based solutions are used, then fault tolerance is improved, but cost increases
Solution Approach 1:
The invention uses multiple relatively inexpensive DAS servers with local storage controllers instead of expensive SAN infrastructure. Each server acts as a temporary holder of storage resources that can be rapidly reassigned. This approach replaces costly, centralized SAN hardware with multiple affordable, distributed DAS components that provide equivalent fault tolerance through software-managed failover.
Solution Approach 2:
The port expander acts as an intermediary device that enables multiple DAS servers to access a shared storage pool through virtualization and zoning. This intermediary provides SAN-like multipathing and failover capabilities without requiring actual SAN hardware, allowing cost-effective implementation of redundant storage access by mediating between multiple servers and the storage devices.
3Quantity of substance
If centralized storage systems are used, then storage capacity is increased, but system complexity increases
Solution Approach 1:
The centralized storage system is segmented into distributed DAS servers, each managing its own local storage resources. The port expander segments the storage pool into manageable zones that can be independently configured. This segmentation reduces overall system complexity by distributing management responsibilities while maintaining aggregate storage capacity through the combined resources of multiple servers.
Solution Approach 2:
Each DAS server independently manages its own storage controller and local storage devices without requiring centralized control. The servers self-configure their storage zones through the port expander and can independently handle failover scenarios. This self-service approach reduces system complexity by eliminating the need for complex centralized management infrastructure while maintaining total storage capacity across all servers.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Providing active-active failover capability to non-failover capable direct-attached storage (DAS) servers including connecting a first and a second non-failover capable direct-attached storage (DAS) servers to a shared storage pool via an expander that supports storage zoning, configuring a first storage zone including the first DAS server and a first portion of the shared storage pool, configuring a second storage zone including the second DAS server and a second portion of the shared storage pool, detecting that the second DAS server has failed, zoning out the second portion of the shared storage pool and mapping the second portion of the shared storage pool to the first storage zone.