Geographically Diverse Storage Convolution Scaling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data storage techniques face challenges in efficiently managing storage space and data redundancy across geographically diverse storage zones, particularly in recovering data from convolved chunks and redistributing data during system scaling.
Innovation Solution
The implementation of a geographically diverse storage system that utilizes convolution and deconvolution techniques to compress data, allowing for efficient storage and recovery of data across multiple zones, while also enabling the addition of new storage zones and redistribution of data to maintain redundancy and geographic diversity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is convolved and stored in a single zone, then storage space is reduced, but data recovery capability deteriorates when that zone fails
Solution Approach 1:
The patent divides convolved data into multiple chunks and distributes them across multiple geographically diverse zones. Instead of storing all convolved chunks in a single zone, the system segments the data storage across multiple zones, so that if one zone fails, the data can still be recovered from other zones using the convolution relationship between chunks.
Solution Approach 2:
The patent applies different storage strategies to different zones based on their geographic distribution and failure characteristics. Each zone stores specific convolved chunks that are optimized for local recovery scenarios, allowing data to be recovered from any single zone failure while maintaining overall system reliability.
2Reliability
If multiple zones are added to a geographically diverse storage system, then data redundancy and recovery capability are improved, but system complexity increases
Solution Approach 1:
The patent pre-calculates and pre-determines the topology and data distribution strategy before zones are actually added to the system. When a new zone is added, the system has already prepared the convolution relationships and chunk distribution mappings, allowing for seamless integration without complex real-time calculations or reorganization of existing data.
Solution Approach 2:
The patent implements a dynamic topology that automatically adapts to zone additions and failures. The system can dynamically adjust which zones store which convolved chunks based on current system state, allowing zones to be added or removed without manual reconfiguration while maintaining optimal data distribution and recovery capability.
3Adaptability or versatility
If data is redistributed during scaling operations, then geographic diversity is maintained, but data movement overhead increases
Solution Approach 1:
The patent pre-determines the optimal data distribution topology before scaling operations begin. When zones are added or removed, the system has already calculated the ideal chunk placement, minimizing the amount of data that needs to be moved during the actual scaling operation. This preliminary planning reduces the time and overhead associated with data redistribution.
4Quantity of substance
If convolution is used to compress data, then storage efficiency is improved, but data recovery complexity increases
Solution Approach 1:
The patent segments the convolved data into manageable chunks distributed across multiple zones, where each chunk can be independently recovered. This segmentation simplifies the recovery process by allowing the system to retrieve data from a single zone rather than having to decode the entire convolved dataset, reducing recovery complexity while maintaining storage efficiency.
Data Source
AI summary
Bulk scaling out of a geographically diverse storage system is disclosed. Bulk scaling out can result in addition of at least two zone storage components to the geographically diverse storage system. Bulk scaling out can provide an avenue to move and compact data to benefit the geographically diverse storage system. Benefits can include faster access to data, faster recovery time for data that becomes less accessible, reduced computing resource demands, etc. Chunks can be moved for greater diversity in a bulk scaled out system. The greater diversity can allow for compaction of data protection chunks, which can result in consuming less storage space to protect more diversified data storage. In some embodiments data from existing zone storage components can be moved to added zone storage components. In some embodiments, protection data from existing zone storage components can be moved to added zone storage components in a more compacted condition.