Redundant Data Updates for Low-I/O Cloud Storage Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data protection methods in cloud storage are resource-intensive due to high I/O consumption and memory usage when updating redundant data segments, particularly when changes occur in raw data, leading to inefficiencies and maintenance complications.
Innovation Solution
A method and apparatus that updates redundant data by generating a second data segment indicating bit identity between raw and changed data segments, expanding it to match the raw data segment length, generating redundant data, and using this information to update the redundant data portion, thereby reducing I/O and memory requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional erasure code operations are performed to update redundant data when raw data changes, then data protection is maintained, but I/O consumption and memory usage increase significantly
Solution Approach 1:
The patent segments the data update process into identifying only the changed data segments rather than processing entire data blocks. By detecting and isolating specific modified segments, the system performs erasure code operations only on necessary portions, significantly reducing I/O consumption while maintaining data protection integrity.
Solution Approach 2:
The patent applies partial action by performing erasure code operations only on the minimal necessary data segments that have changed, rather than reprocessing all data. This selective approach reduces computational overhead and I/O operations while still ensuring complete data protection for the updated portions.
2Reliability
If traditional erasure code operations are performed to update redundant data when raw data changes, then data protection is maintained, but memory usage increases significantly
Solution Approach 1:
The patent divides the data processing into discrete segments and maintains memory only for the changed segments rather than loading entire data blocks. This segmentation allows the system to process and protect data with minimal memory footprint, updating redundant data while keeping memory usage low.
Solution Approach 2:
The patent uses partial action by computing erasure codes only for the specific changed segments that need updating, rather than recalculating codes for all data. This approach dramatically reduces the quantity of data held in memory during processing while maintaining complete data protection.
3Reliability
If frequent updates to redundant data are performed to maintain data correctness, then data consistency is improved, but system complexity and maintenance difficulty increase
Solution Approach 1:
The patent implements self-service through automatic detection of changed data segments and trigger-based updates of redundant data. The system autonomously identifies modifications and performs necessary erasure code operations without complex manual intervention or scheduling, maintaining data consistency while reducing operational complexity.
Solution Approach 2:
The patent uses feedback mechanisms where the system continuously monitors for data changes and automatically triggers redundant data updates when changes are detected. This feedback loop ensures data consistency is maintained dynamically without requiring complex proactive update scheduling or manual management.
Data Source
AI summary
A technique of managing storage includes receiving a request to change an initial portion of data, the initial portion of data (i) associated with an initial redundant region and (ii) including a first segment to be changed and a set of other segments not to be changed; updating the first segment in response to the request; and generating an updated redundant region based on a computation involving the initial redundant region and the first segment but not involving the set of other segments.