Cloud-Based Replica Storage for Dynamic Service Level Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional cloud storage systems lack advanced management features and fail to utilize remote cloud storage effectively for continuous data mirroring and failover protection, limiting their ability to perform advanced data management functions like RAID array management and ensuring continuous operations.
Innovation Solution
The implementation of a cloud-based replica storage system that allocates storage space on cloud devices, maps it to virtual local addresses, groups these addresses into cloud-based ranks, and designates them as replica storage, dynamically adjusting service levels based on data characteristics and mirroring rates to enable seamless swapping with primary storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If cloud storage is used for replica storage, then storage capacity and availability are improved, but service level consistency and performance are worsened
Solution Approach 1:
The system dynamically adjusts the service level of cloud-based replica storage based on operational needs. When the primary storage is operational, a baseline service level is assigned. When the primary storage fails or requires maintenance, the service level is automatically increased to support failover operations, ensuring performance consistency across different operational states
Solution Approach 2:
The service level parameter of cloud storage is made variable rather than fixed. The system changes service level parameters (such as IOPS, throughput, latency requirements) based on the operational state of the primary storage, allowing the same cloud storage resource to provide different performance characteristics as needed
2Reliability
If cloud storage is designated as replica storage, then failover protection is improved, but data management complexity is worsened
Solution Approach 1:
The system automatically manages cloud-based replica storage without requiring manual intervention. The storage system self-configures the replica storage, automatically monitors its state, and performs failover operations when needed, reducing the burden of data management complexity on operators
Solution Approach 2:
The cloud-based replica storage serves multiple functions: it acts as backup storage during normal operations, provides failover capability when primary storage fails, and can be dynamically adjusted to support different service levels. This multi-functionality is managed through a unified system that handles diverse operations through a single management interface
3Adaptability or versatility
If service level is dynamically adjusted, then operational flexibility is improved, but system complexity is worsened
Solution Approach 1:
The service level is transformed from a static configuration parameter to a dynamic property that automatically adjusts based on system state. The system continuously monitors operational conditions and adjusts service levels in real-time, providing flexibility without requiring complex manual reconfiguration
Solution Approach 2:
The system implements feedback mechanisms that monitor the operational state of primary and replica storage systems. Based on this feedback, the system automatically adjusts service levels to maintain optimal performance. The feedback loop ensures that service level changes are responsive to actual system conditions rather than predetermined configurations
Data Source
AI summary
A computer-implemented method for using cloud based ranks as replica storage comprises allocating storage space on cloud storage devices via a cloud interface; mapping the allocated storage space on the cloud storage devices to corresponding virtual local addresses; grouping the virtual local addresses to create at least one cloud based rank from the allocated storage space on the cloud storage devices; designating a cloud based rank as cloud based replica storage for a corresponding primary storage; assigning a service level to the cloud based replica storage based, at least in part, on characteristics of data being mirrored to the cloud based replica storage and a rate at which the data is mirrored to the cloud based replica storage; and dynamically adjusting the service level assigned to the cloud based replica storage in response to a command to swap the cloud based replica storage with the corresponding primary storage.