Distributed Storage Controller Fragmentation for Data Availability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems face disruptions and increased costs due to data availability issues during array management, backup, and mirroring processes, particularly in cluster storage systems, where data transfer delays and excess loads on cross-town data links cause inefficiencies and a shortage of unit control blocks (UCBs).
Innovation Solution
A method and system for distributing data across multiple storage controllers by fragmenting it, allowing each controller to own a portion of the data, where requests are routed to the owning controller, and write operations are coordinated among controllers to reduce load on infrastructure and improve data access efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is stored in a single storage controller or array, then data access is simple and direct, but data availability is disrupted during array management, backup, or transfer operations
Solution Approach 1:
The patent divides data into multiple fragments and distributes them across different storage controllers. Each fragment is stored independently, allowing the system to maintain data availability even when individual controllers are offline for maintenance or experiencing failures. This segmentation enables parallel access paths and eliminates single points of failure.
2Reliability
If data is mirrored across multiple storage controllers, then data availability and redundancy are improved, but the load on cross-town data links increases and costs rise
Solution Approach 1:
The patent implements local quality by allowing each storage controller to serve data requests for its locally stored fragments without requiring cross-town communication. This reduces bandwidth consumption on cross-town links while maintaining data availability, as only the specific fragment needing access is transmitted locally rather than requiring remote mirror access.
3Reliability
If data is accessed from a remote storage controller in a hyperswap setup, then data redundancy is maintained, but I/O operations experience delays due to distance
Solution Approach 1:
The patent segments data across multiple storage controllers located at different sites, with each controller holding a fragment. This allows I/O operations to access local fragments without remote communication delays, while still maintaining redundancy through distributed storage. The segmentation eliminates the need for remote I/O operations that cause latency in traditional hyperswap configurations.
4Ease of manufacture
If storage arrays are taken offline for maintenance or management, then necessary repairs or updates can be performed, but enterprise operations are disrupted and time is lost
Solution Approach 1:
The patent divides data storage across multiple independent controllers, allowing individual controllers to be taken offline for maintenance without affecting overall system availability. Other controllers continue to serve data requests, enabling maintenance activities to proceed without disrupting enterprise operations or causing time losses.
Solution Approach 2:
The distributed fragment storage system acts as an intermediary mechanism, where data fragments stored on multiple controllers provide backup access paths. When one controller is offline, the system automatically routes requests through alternative controllers, maintaining continuous operation without interruption.
Data Source
AI summary
A method and system for distributing and accessing data over multiple storage controllers wherein data is broken down into one or more fragments over the multiple storage controllers, each storage controller owning a fragment of the data, receiving a request for data in a first storage controller from one of a plurality of hosts, responding to the host by the first storage controller with the request if the first storage controller contains the requested data, forwarding the request to the second storage controller from the first storage controller if the first storage controller does not contain the requested data, responding to the first storage controller from the second storage controller with the request, and responding to the host from the first storage controller with the request.