Multi-level Distributed Hash Table for Hierarchical Network Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional distributed hash table (DHT) systems are inefficient, especially as the number of nodes in a DHT ring becomes large, due to their flat structure, which hinders effective data storage and retrieval.
Innovation Solution
Implementing multiple DHT rings at different levels of a network hierarchy, where each level uses distinct hashing operations and functions to identify nodes for data storage, improving efficiency by narrowing the number of candidate nodes at each level and promoting load balancing and fault tolerance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a flat DHT ring structure is used for data storage, then the system is simple to implement, but the efficiency deteriorates as the number of nodes becomes large
Solution Approach 1:
The patent divides the flat DHT ring into multiple hierarchical levels, creating a multi-level DHT structure where nodes are organized into tiers. Each level handles a subset of the keyspace, segmenting the overall storage task into manageable portions that can be processed more efficiently at each level.
Solution Approach 2:
The patent transitions from a single-dimensional flat ring structure to a multi-dimensional hierarchical structure by adding vertical levels to the existing horizontal ring. This dimensional expansion allows nodes to be organized both horizontally within levels and vertically across levels, enabling more efficient routing and storage operations.
2Productivity
If multiple DHT rings at different hierarchical levels are implemented, then data storage efficiency is improved, but the system complexity increases
Solution Approach 1:
The patent implements a nested hierarchical structure where lower-level DHT rings are contained within higher-level rings. Each level nests its nodes and keyspace management within the broader context of the parent level, creating a compact multi-level system that improves efficiency while containing complexity through organized nesting.
Solution Approach 2:
The patent assigns different properties and functions to nodes at different hierarchical levels. Higher-level nodes handle broader keyspace ranges and coordination tasks, while lower-level nodes manage more specific data storage operations. This local differentiation optimizes performance at each level without requiring uniform complexity throughout the entire system.
3Reliability
If data is distributed across a large number of nodes in a flat structure, then fault tolerance is improved, but network traffic increases and hotspots are created
Solution Approach 1:
The patent segments the network traffic by organizing nodes into hierarchical levels, where each level handles a specific portion of data routing and storage. This segmentation prevents traffic from traversing the entire flat ring, reducing overall network traffic while maintaining distributed fault tolerance across the hierarchical structure.
Solution Approach 2:
The patent introduces intermediate nodes at higher hierarchical levels that act as mediators between client requests and lower-level storage nodes. These intermediary nodes route traffic more efficiently by processing requests at the appropriate level, preventing unnecessary traffic propagation across the entire network while maintaining fault tolerance through the distributed hierarchical structure.
Data Source
AI summary
An improved technique for distributed data storage employs multiple DHT (distributed hash table) rings provided at different levels of a network hierarchy. A computing node is identified for data storage by performing multiple hashing operations, one for each DHT ring. The hashing operations for the different rings are distinct in that they are performed using different hashing functions and/or are performed on different data sources. In one example, a 2-level DHT is formed from a group of LANs forming a first DHT ring and a group of computing nodes, within each LAN, forming a second DHT ring.