Dynamic Replica Allocation for Distributed Storage Capacity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud storage systems face inefficiencies in managing redundancy, leading to high storage capacity requirements and increased costs due to maintaining multiple copies of files, especially as data volume grows exponentially, with popular files being rarely accessed and wasting significant storage capacity on backup copies.
Innovation Solution
A method and apparatus for dynamically adjusting the number of copies of electronic documents in a distributed storage system by targeting specific document popularity and availability, allowing for 'altruistic replication' where popular files donate replication opportunities to less popular ones, optimizing storage capacity usage while maintaining high availability and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple copies of every file are maintained to protect against storage device failure, then data reliability is improved, but storage capacity requirements increase significantly
Solution Approach 1:
The patent applies local quality by differentiating between popular and unpopular files, allocating different numbers of replicas based on file popularity. Popular files receive more replicas for high availability, while unpopular files receive fewer replicas, optimizing storage capacity while maintaining data reliability where it matters most.
Solution Approach 2:
The system dynamically adjusts the number of file replicas based on changing popularity metrics and access patterns. As files transition between popular and unpopular status, their replica counts are adjusted accordingly, allowing the system to adapt to changing storage demands and optimize both reliability and storage capacity over time.
2Device complexity
If a fixed number of replicas is maintained for all files, then data protection is simplified, but storage efficiency deteriorates due to wasted capacity on rarely accessed files
Solution Approach 1:
The patent implements dynamic replica management where the number of replicas for each file is adjusted based on popularity metrics. This dynamic approach improves storage efficiency by reducing replicas for unpopular files while maintaining adequate protection for popular files, without significantly increasing system complexity through automated popularity tracking and adjustment algorithms.
Data Source
Figure 1
Figure 2
AI summary
Methods and apparatus (10) are disclosed for storing electronic documents in a distributed electronic storage system comprising a plurality of electronic storage devices (16) together providing a total storage capacity, the system having a target number of copies in respect of each document stored therein; the method comprising: determining the current number of copies of a requested document stored in the system and increasing the number of copies of that document unless the number of copies of that document is already at or above the target number of copies in respect of that document; and otherwise selecting at least one other document the number of copies stored in the system of which is below the target number of copies in respect of that at least one other document, and increasing the number of copies of that at least one other document instead.