Cloud Storage Data Distribution by Capacity Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud storage systems do not efficiently distribute data across data centers based on storage capacities, leading to inefficiencies such as data fragmentation and underutilization of storage resources.
Innovation Solution
A method and apparatus that divide objects into sub-objects based on fragmentation size and distribute them across data centers according to their storage capacities, using weights assigned to each data center to determine the allocation of sub-objects, with metadata management for correlation and storage location determination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is distributed to storage devices in proportion to storage capacity, then storage utilization should be optimized, but the system cannot store data in storage devices with available space once a predetermined storage time is reached
Solution Approach 1:
The patent implements dynamic data distribution that adapts to real-time storage capacity conditions. Instead of static proportional distribution, the system continuously monitors storage device availability and dynamically adjusts distribution ratios. When storage devices have available capacity, the system modifies distribution parameters to utilize remaining space, transforming the static proportional allocation into a dynamic adaptation process that responds to changing storage conditions.
Solution Approach 2:
The system changes distribution parameters based on storage device status. By monitoring storage capacity, access frequency, and availability metrics, the system adjusts distribution parameters to optimize both utilization and reliability. This parameter adaptation allows the system to continue distributing data to devices with available space while maintaining data availability requirements.
2Quantity of substance
If data is fragmented and distributed across multiple storage devices, then storage capacity is utilized, but data retrieval requires accessing multiple devices increasing complexity
Solution Approach 1:
The patent introduces a storage management server as an intermediary that handles data distribution and retrieval coordination. This intermediary maintains metadata about data fragment locations and manages the complexity of multi-device operations. By centralizing the coordination function in the storage management server, the system achieves efficient data distribution across multiple devices while the intermediary absorbs the retrieval complexity, presenting a simplified interface to clients.
3Quantity of substance
If storage devices are added to increase capacity, then storage capability improves, but system costs increase
Solution Approach 1:
The patent implements continuous monitoring and utilization of storage device capacity to ensure existing storage resources are fully exploited before adding new devices. The system maintains continuous data distribution operations that adapt to available capacity, preventing premature expansion. This continuity principle ensures that storage devices operate at optimal utilization levels, delaying the need for costly capacity expansion and maximizing the useful action of existing storage infrastructure.
Data Source
AI summary
Provided are apparatus and method for distributedly storing an object in a plurality of data centers included in a cloud storage system. In the method, an object may be divided into a plurality of sub-objects each having a fragmentation size. Then, the sub-objects may be distributedly stored in at least one data center based on weights of the plurality of data centers.