Data Caching System with Erasure Code Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data caching systems are vulnerable to data loss due to device failures, as cached data in internal memory devices is often unprotected, leading to permanent loss if not adequately secured.
Innovation Solution
A data caching system comprising N data storage devices and M erasure code devices, where a data stripe spans multiple devices, with erasure code data generated to ensure data durability, and a software module configures writing data chunks across these devices for high availability and redundancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is cached in internal memory devices of separate computing devices, then data access speed is improved, but data reliability deteriorates due to lack of protection against device failures
Solution Approach 1:
The patent segments data into multiple data chunks and distributes them across N data storage devices and M erasure code devices. This segmentation allows fast local access while distributing risk across multiple devices, resolving the contradiction between speed and reliability.
Solution Approach 2:
The patent applies erasure coding to create redundant data representations before data is written to storage devices. This beforehand cushioning ensures that even if some devices fail, the original data can be recovered, thus improving reliability without sacrificing access speed.
2Reliability
If erasure code devices are added to the data storage system, then data durability is improved, but system complexity increases
Solution Approach 1:
The patent creates simplified copies of data through erasure coding, where M erasure code devices store redundant information that can reconstruct the original data. This copying approach improves durability while keeping the complexity manageable through standardized encoding procedures.
3Reliability
If data is distributed across multiple storage devices, then data protection is improved, but write operation complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-defining data stripes that span across N data storage devices and M erasure code devices before data is written. This preliminary configuration simplifies the write operation, as the system only needs to follow the pre-established stripe structure rather than dynamically determining data distribution.
Data Source
AI summary
A system, computer program product, and computer-implemented method for defining a data stripe that spans one or more of N data storage devices and one or more of M erasure code devices. The one or more N data storage devices and the one or more M erasure code devices are included within a data storage system. A data chunk to be written to the data storage system is received. At least a portion of the data chunk is written to the portion of the data stripe that spans the one or more N data storage devices. Each of the N data storage devices and the M erasure code devices is included within a unique server computer.