Shared Parity Object Storage for Cloud DVR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In large-scale cloud DVR storage systems, the repeated storage of identical parity data leads to significant disk overhead and increased computational resources, driving up costs and reducing the storage capacity for multimedia data objects.
Innovation Solution
The method involves generating and storing compressed parity data for identical content instances, distributing data copies across multiple storage entities, and using a manifest to link parity objects with data objects, thereby reducing disk overhead and increasing storage efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple copies of identical parity data are stored for each data object, then fault tolerance and data recovery capability are improved, but disk overhead and storage capacity are significantly increased
Solution Approach 1:
The patent merges identical parity data from multiple data objects into a single shared parity object. Instead of storing separate parity copies for each identical data object, the system generates one parity object that serves multiple data objects, thereby reducing disk overhead while maintaining fault tolerance through shared redundancy
Solution Approach 2:
The patent implements universal parity objects that perform multiple functions simultaneously. A single parity object can protect multiple different data objects, making the parity data multi-functional. This approach allows the same parity structure to serve various data recovery needs without requiring separate parity copies for each data object
2Reliability
If multiple copies of identical parity data are stored for each data object, then data recovery capability is improved, but computational resources and processing overhead are increased
Solution Approach 1:
The patent combines the parity generation process for multiple identical data objects into a single computational operation. By merging the parity calculation tasks, the system performs one set of computations instead of multiple separate computations, thereby reducing processing overhead and computational resource consumption while still providing recovery capability for all protected data objects
3Reliability
If multiple copies of identical data objects are stored, then compliance with copyright regulations and fault tolerance are improved, but storage capacity for multimedia data objects is reduced
Solution Approach 1:
The patent merges the storage function of identical parity data across multiple data objects into a single shared storage location. By consolidating redundant parity copies into one shared parity object, the system recovers storage capacity that can then be used to store additional multimedia data objects, thereby increasing overall storage capacity while maintaining fault tolerance through the shared parity structure
Data Source
AI summary
A disclosed method is performed at a fault-tolerant object-based storage system including M data storage entities, each is configured to store data on an object-basis. The method includes obtaining a request to store N copies of a data object and in response, storing the N copies of the data object across the M data storage entities, where the N copies are distributed across the M data storage entities. The method additionally includes generating a first parity object for a first subset of M copies of the N copies of the data object, where the first parity object is stored on a first parity storage entity separate from the M data storage entities. The method also includes generating a manifest linking the first parity object with one or more other subsets of M copies of the N copies of the data object.