Distributed Storage Zone Grouping for Data Availability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional distributed storage systems face delays and reliability issues due to storing objects and replicas regardless of client and data node locations, leading to potential data unavailability when a network zone fails.
Innovation Solution
A distributed storage system that groups data nodes into zones based on location and stores objects and replicas across different zone groups to minimize delays and ensure data availability by selecting optimal virtual channels and data nodes for storage and replication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If objects and replicas are stored in data nodes separated from the client at a long distance, then storage capacity and distribution are improved, but processing time and data access delay increase
Solution Approach 1:
The patent applies local quality by selecting data nodes based on their physical proximity to the client. The system determines the client's location and chooses data nodes in nearby regions for storing objects and replicas, thereby reducing data access delay while maintaining adequate storage capacity through localized distribution rather than global dispersion
2Productivity
If objects and replicas are stored in data nodes gathered in one specific zone, then storage efficiency and network utilization are improved, but system reliability and data availability decrease when network fails
Solution Approach 1:
The patent segments the storage system into multiple geographic zones or regions. When storing objects and replicas, the system deliberately distributes them across different zones rather than concentrating them in one specific zone. This segmentation strategy ensures that if one zone experiences network failure, data remains accessible through other zones, thereby maintaining both storage efficiency and system reliability
3Speed
If location information is considered for data node selection, then data access speed and reliability are improved, but system complexity and selection process difficulty increase
Solution Approach 1:
The patent implements self-service by having the system automatically determine the client's location and autonomously select appropriate data nodes based on that location information. The system performs location-based selection without requiring manual intervention or complex user input, thereby achieving improved data access speed while minimizing the complexity burden on users through automated location awareness and node selection
Data Source
AI summary
A distributed storage system and a method for storing objects based on locations. The distributed storage system may include a plurality of data nodes, at least one selection agent, a client, and a proxy server. The plurality of data nodes may be configured to be grouped into a plurality of zone groups based on locations of the plurality of data nodes and configured to store a target object and replicas of the target object. The at least one selection agent may be configured to select multiple target zone groups and select one target data node for each one of the selected multiple target zone groups.