Network Storage Server System with Distributed Object Store
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network storage systems face inefficiencies due to hierarchical data organization, which leads to duplication of content and administrative overhead, and lack the ability to seamlessly apply policies across data objects, limiting data management and retrieval efficiency.
Innovation Solution
A network storage server system incorporating a distributed object store with location-independent addressing, a presentation layer providing multiple access interfaces, a metadata subsystem for search and retrieval, and a policy-based management subsystem that autonomously manages data objects based on user-specified policies, allowing transparent data migration and efficient data management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If hierarchical organization (path names) is used for data storage, then data navigation and retrieval are enabled, but data duplication and administrative overhead increase
Solution Approach 1:
The patent segments the data management system into two independent components: (1) a hierarchical namespace for navigation and retrieval operations, and (2) a flat object store for actual data storage. This segmentation allows the namespace to provide structured access paths without forcing the underlying storage to maintain hierarchical organization, thereby eliminating data duplication while preserving ease of navigation.
Solution Approach 2:
The patent introduces an intermediary layer (the namespace) between the user/application and the actual data storage. This namespace acts as a mediator that provides hierarchical navigation capabilities without requiring the underlying object store to duplicate data in hierarchical structures. The namespace maps logical paths to physical storage locations, eliminating the need for hierarchical data duplication.
2Device complexity
If path names are tied to storage locations, then data access control and management are simplified, but data migration becomes opaque and complex
Solution Approach 1:
The patent introduces a namespace as an intermediary layer that decouples logical data access paths from physical storage locations. The namespace provides stable logical paths for access control and management while allowing the underlying object store to migrate data transparently. When data migrates, only the namespace mapping needs to be updated, not the access control structures or application logic.
Solution Approach 2:
The patent adds a new dimensional layer (the namespace layer) above the physical storage layer. This creates a two-dimensional architecture where logical paths exist in one dimension and physical storage in another. Data migration occurs in the physical dimension without affecting the logical dimension, making migration transparent to access control and management systems.
3Productivity
If storage systems mix different storage devices, then data accessibility and performance are improved, but policy application becomes cumbersome and requires administrator intervention
Solution Approach 1:
The patent enables the storage system to automatically apply policies to data objects without requiring administrator intervention. The system includes policy evaluation logic that autonomously determines which policies apply to which data objects and executes them accordingly. This self-service capability allows the system to automatically manage data placement, replication, and migration across mixed storage devices based on predefined policies.
Solution Approach 2:
The patent implements dynamic policy application where policies can be defined at the data object level and automatically adjusted based on changing conditions. The system continuously evaluates data objects against relevant policies and automatically adjusts data placement and management actions. This dynamic approach eliminates the need for static, administrator-managed policy configurations while maintaining data accessibility and performance across mixed storage devices.
4Ease of operation
If traditional filesystem hierarchy is used, then data organization for navigation is achieved, but inefficiencies such as content duplication occur
Solution Approach 1:
The patent segments the data management architecture into a hierarchical namespace component and a flat object store component. The namespace provides the hierarchical organization needed for navigation and retrieval, while the object store maintains data in an efficient flat structure without duplication. This segmentation allows each component to optimize for its specific function without the drawbacks of a unified hierarchical filesystem.
Solution Approach 2:
The patent creates a logical copy (the namespace) of the data hierarchy that does not duplicate the actual data content. The namespace contains only metadata and path information, while the actual data objects are stored once in the flat object store. This allows hierarchical navigation without duplicating data, improving data management efficiency while maintaining ease of organization.
Data Source
AI summary
A network storage server system includes a distributed object store, a presentation layer, a metadata subsystem, and a content management subsystem. The object store has no namespace and provides location-independent addressing of data objects. The presentation layer provides multiple interfaces for accessing data stored in the object store, including a NAS interface and a Web Service interface, and provides at least one namespace for accessing data via the NAS interface or the Web Service interface. The Web Service interface allows access to stored data via the namespace or without using the namespace (“raw object” access). The metadata subsystem stores user-specified and/or system-generated metadata relating to data objects and allows data objects to be identified and retrieved by searching on the metadata. The content management subsystem autonomously manages lifecycles of data objects according to user-specified policies, based on metadata associated with the data objects and tracked by the metadata subsystem.