Storage Resource Management for Cloud Data Persistence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems face challenges in efficiently managing data across multiple storage devices, particularly in ensuring data persistence, reliability, and scalability in cloud-based environments.
Innovation Solution
The proposed solution involves a storage system architecture that utilizes a plurality of block storage devices, with application-aware storage methods that include direct-mapped flash storage systems, zoned storage devices, and dual PCI flash storage devices. This architecture offloads device management responsibilities from storage drives, employs non-volatile RAM as a buffer for write operations, and implements erasure coding and mirroring for data redundancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If applications are allowed to directly access shared storage resources without constraints, then application performance and data access speed are improved, but storage resources may be overconsumed leading to system instability
Solution Approach 1:
The patent introduces a storage resource management system that acts as an intermediary between applications and shared storage resources. This mediator monitors storage consumption, enforces policies, and prevents overconsumption while maintaining efficient data access. The intermediary layer balances performance needs with resource protection, resolving the contradiction between speed and reliability.
2Productivity
If storage resources are heavily utilized to maximize capacity, then storage efficiency is improved, but the system becomes vulnerable to resource exhaustion and failure
Solution Approach 1:
The patent implements preventive measures by establishing storage consumption thresholds and policies before resource exhaustion occurs. The system proactively monitors usage patterns, predicts potential overconsumption, and takes corrective actions in advance. This cushioning approach maintains high storage efficiency while preventing catastrophic failure, resolving the contradiction between productivity and reliability.
3Loss of time
If storage access is highly optimized for performance, then write latency is reduced, but data consistency and persistence may be compromised
Solution Approach 1:
The patent employs preliminary actions by pre-establishing data persistence policies, redundancy mechanisms, and consistency protocols before write operations occur. The system prepares persistence structures in advance and uses buffering strategies that maintain data integrity while optimizing write performance. This preliminary preparation resolves the contradiction between minimizing time loss and ensuring reliable data persistence.
Data Source
AI summary
Preventing applications from overconsuming shared storage resources, including: identifying one or more sub-regions of data stored on a storage device that are associated with an application of a known application type; compiling information describing the application's utilization of a storage system; determining that a storage system objective has not been met; and initiating, based on the information describing the application's utilization of the storage system, remediation actions.