Host-Offloaded Storage Array Architecture for Scalability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage array architectures face limitations in scalability as processing capabilities do not scale with the aggregate performance of storage drives, leading to bottlenecks in handling increased throughput and fault tolerance, which increases costs and complexity.
Innovation Solution
A storage system architecture that separates control and data paths, allowing servers to access storage devices directly via a network, with storage controllers handling control path operations and servers implementing data path operations, including a data redundancy engine for RAID 5 or RAID 6 schemes, to enhance scalability and performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional storage array architecture with storage controllers is used, then data processing and control functions are integrated, but processing capabilities do not scale with aggregate storage drive performance
Solution Approach 1:
The patent segments the storage system into separate control plane (storage controllers) and data plane (storage devices accessed directly by hosts) components. This allows the data path to scale independently by enabling hosts to access storage devices directly via network, bypassing the storage controllers for data transfer operations, while the control plane maintains management functions.
Solution Approach 2:
The patent extracts the data path processing functions from the storage controllers and places them directly in the hosts. By implementing data redundancy schemes (RAID 5/6) and data path storage commands in the hosts themselves, the storage controllers are relieved of heavy processing loads, allowing the system to scale processing capability with aggregate storage performance.
2Productivity
If more storage drives are attached to increase aggregate throughput, then storage capacity and speed increase, but storage controller processing capabilities remain the same creating a bottleneck
Solution Approach 1:
The patent enables hosts to perform self-service for data path operations including implementing data redundancy schemes (RAID 5/6), handling data path storage commands, and managing fault tolerance. This allows the system to scale throughput by adding storage drives without proportionally increasing storage controller processing requirements, as hosts independently handle these functions.
3Ease of operation
If storage controllers handle all data path processing, then centralized control is maintained, but computational effort and costs increase
Solution Approach 1:
The patent introduces a new dimension of operation by enabling hosts to access storage devices directly via network, creating a parallel data path that operates independently from the traditional controller-mediated path. This dimensional change allows centralized control to be maintained for management functions while distributing computational effort to hosts for data path operations.
Data Source
AI summary
The invention relates to a storage system comprising one or more storage controllers, two or more storage devices and two or more storage clients, the storage controllers, the storage devices and the storage clients being coupled via a network in order to exchange information between the storage controllers, said storage devices and said storage clients, wherein each storage client is adapted to provide data-path-storage commands to the storage devices via the network bypassing the storage controllers, wherein the storage system is adapted to provide data redundancy using a data redundancy scheme higher than RAID 1.