ROC Cluster Architecture for RAID Bandwidth and Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
RAID systems face limitations in scalability, flexibility, and performance due to bandwidth constraints of RAID controllers, which can lead to bottlenecks and limitations in the number of virtual disks that can be managed and affect availability.
Innovation Solution
Implementing a RAID-on-chip (ROC) cluster that includes multiple RAID-on-chip devices and IO controllers, allowing for distributed workload management and communication among heterogeneous devices, enabling parallel processing and offloading physical disk management, thereby enhancing scalability, customizability, and performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single RAID controller manages virtual disks, then the system structure is simple, but the bandwidth is limited and scalability is restricted
Solution Approach 1:
The patent divides the RAID controller functionality into multiple independent RAID-on-chip devices, each capable of managing virtual disks autonomously. This segmentation allows the system to achieve higher bandwidth and scalability by distributing workload across multiple devices while maintaining relatively simple individual device structures.
Solution Approach 2:
The patent transitions from a single-controller one-dimensional architecture to a multi-device cluster forming a two-dimensional or three-dimensional scalable structure. This dimensional expansion enables the system to overcome bandwidth limitations by adding more processing nodes and communication pathways.
2Productivity
If multiple RAID controllers are added to increase bandwidth, then the bandwidth and scalability improve, but the system complexity and cost increase
Solution Approach 1:
The patent merges multiple RAID-on-chip devices into a unified cluster that presents a single virtual disk interface to the host. This merging approach allows the system to achieve high bandwidth through parallel processing while maintaining simple system management and relatively low cost by sharing resources and using standardized interfaces.
Solution Approach 2:
Each RAID-on-chip device in the cluster is designed with universal functionality to manage virtual disks independently. This multi-functionality allows any device in the cluster to handle any virtual disk workload, enabling flexible load distribution and reducing the need for specialized components, thereby controlling system complexity and cost.
3Device complexity
If a virtual disk is managed by only one RAID controller, then the management is simple, but the availability is reduced when the controller experiences problems
Solution Approach 1:
The patent establishes preliminary workload distribution mechanisms and failover protocols among RAID-on-chip devices before failures occur. When a controller experiences problems, the system can immediately redistribute its virtual disk workload to other healthy devices in the cluster, maintaining availability without complex real-time decision-making.
Solution Approach 2:
The patent implements redundancy and load balancing capabilities in advance, creating a cushion against controller failures. Multiple devices are prepared to handle additional workload, ensuring that when one controller fails, the system can absorb the shock and maintain operation with reduced complexity in the failure response.
Data Source
AI summary
Devices, systems, and corresponding methods, including without limitation RAID devices, I/O controllers, and RAID clusters, that can provide enhanced storage solutions. A RAID device might be a RAID-on-chip device. A RAID cluster can comprise a plurality of RAID devices and/or I/O controllers that can provide one or more virtual disks for use by a host. In some cases, a RAID cluster can be a ROC cluster, which includes one or more ROC devices.