Policy-Based Intelligent Data Placement Across LANs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional centralized data storage facilities are expensive to maintain, suffer from scalability issues, and are susceptible to failures due to single-point vulnerabilities, such as earthquakes or floods, which can disable data storage for an entire enterprise.
Innovation Solution
Implementing a policy-based intelligent data placement technique that distributes data across selected local area networks (LANs) based on traffic optimization, network bandwidth utilization, and data redundancy policies, allowing for flexible selection of LANs and generation of information elements like data fragments and erasure codes to ensure data recovery and scalability without a central bottleneck.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If data is stored at a centralized facility, then data storage is simplified and centralized management is achieved, but maintenance costs increase and scalability is limited
Solution Approach 1:
The patent segments the centralized storage facility into multiple distributed storage nodes across different LANs. Each node independently stores portions of data, eliminating the need for a single large centralized facility and reducing maintenance costs while maintaining simplified management through policy-based orchestration.
Solution Approach 2:
The patent transitions from a single-dimensional centralized storage model to a multi-dimensional distributed model across multiple LANs. Data is placed across different network segments, adding spatial and organizational dimensions that improve scalability and reduce maintenance burden on any single facility.
2Device complexity
If data is stored at a centralized facility, then centralized management is achieved, but the facility becomes a bottleneck to incoming and outgoing traffic
Solution Approach 1:
The patent segments the monolithic centralized storage into multiple distributed storage nodes across different LANs. This segmentation allows data traffic to be distributed across multiple paths and nodes, eliminating the single-point bottleneck and improving overall data transfer speed and network throughput.
3Device complexity
If data is stored at a centralized facility, then centralized management is achieved, but the facility becomes susceptible to single-point failure
Solution Approach 1:
The patent segments centralized storage into distributed storage nodes across multiple independent LANs. This segmentation eliminates the single-point failure vulnerability by ensuring that failure of any single node or LAN does not compromise the entire data storage system, as data remains accessible through other nodes.
Solution Approach 2:
The patent applies local quality by placing data replicas or fragments across storage nodes with different failure characteristics. By considering failure correlations and selecting nodes with independent failure modes, the system enhances reliability through diversity in the local properties of storage nodes.
4Productivity
If data is distributed across multiple LANs, then scalability is improved and bottlenecks are eliminated, but system complexity increases
Solution Approach 1:
The patent implements self-service through policy-based data placement where the system automatically selects appropriate storage nodes based on predefined policies (traffic optimization, bandwidth utilization, failure correlation). This automation eliminates the need for complex manual management of distributed storage, allowing scalability without proportional increases in operational complexity.
Solution Approach 2:
The patent uses parameter changes by dynamically adjusting data placement decisions based on varying system conditions such as network traffic patterns, bandwidth availability, and failure correlations. This allows the system to adapt to changing conditions and scale efficiently without requiring complex static architecture design.
5Speed
If data is placed based on traffic optimization policy, then network traffic is optimized, but other policies like bandwidth utilization may be compromised
Solution Approach 1:
The patent implements dynamics by allowing the data placement system to adaptively switch between different policies (traffic optimization, bandwidth utilization, failure correlation) based on current system conditions and requirements. This dynamic approach enables the system to optimize for traffic efficiency when needed while maintaining the flexibility to prioritize other concerns like bandwidth utilization or failure independence when appropriate.
Data Source
AI summary
A technique performs policy-based intelligent data placement in an electronic environment. The technique involves selecting, from a pool of candidate local area networks (LANs) of the electronic environment, a plurality of LANs within which to store the data based on a set of policy priority levels assigned to the data. The technique further involves generating a set of information elements (e.g., data fragments, erasure codes, etc.) from the data, and placing the set of information elements on storage nodes of the plurality of LANs. Such a method enables the data to be stored in a distributed manner and alleviates the need for a central storage facility. Since the data is distributed among the storage nodes of the plurality of LANs, system capacity and infrastructure is able to grow (i.e., scale) in a manner which does not create a problematic bottleneck.