LPM Switches for Distributed Storage Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Distributed storage systems face scalability challenges due to reliance on centralized metadata servers and complex routing tables, which hinder efficient file location and data access as storage demands increase.
Innovation Solution
Implementing longest prefix matching (LPM) switches that map file names to storage devices using a forwarding information base, reducing the need for index servers and enabling load balancing across multiple servers, thus simplifying routing and improving scalability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If centralized metadata servers or DHT nodes are used to map file names to server locations, then file location accuracy is improved, but system complexity and scalability deteriorate due to routing table maintenance requirements
Solution Approach 1:
The patent extracts the routing table maintenance burden from individual metadata servers and DHT nodes by introducing a centralized LPM switch that performs longest prefix matching. This centralizes the complex routing decision-making function, relieving individual nodes from maintaining large routing tables while preserving accurate file location mapping.
Solution Approach 2:
The LPM switch acts as an intermediary between clients and storage servers, performing longest prefix matching on directory paths to determine the destination server. This mediator handles the complex routing logic centrally, allowing individual nodes to maintain simpler state while achieving the same file location accuracy as distributed approaches.
2Quantity of substance
If the number of storage servers and files increases to meet growing storage demands, then system capacity is improved, but routing table maintenance complexity and scalability worsen
Solution Approach 1:
The LPM switch automatically performs longest prefix matching on incoming requests using pre-configured directory-to-server mappings. This self-service mechanism eliminates the need for manual routing table updates and complex distributed coordination when adding new servers or files, enabling the system to scale capacity without proportionally increasing operational complexity.
3Adaptability or versatility
If distributed hash tables are used for file mapping, then decentralization is improved, but the need for each node to maintain routing tables increases complexity
Solution Approach 1:
The patent extracts the routing table maintenance function from individual DHT nodes and concentrates it in a centralized LPM switch. This allows the system to maintain decentralized data storage while eliminating the complexity burden from individual nodes, as they no longer need to maintain or query large distributed routing tables.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
A method performed by a switch, the method comprising receiving a request for a file from a client, wherein the file is located in a distributed storage system, extracting a directory for the file from the request, performing longest prefix matching (LPM) of the directory against a forwarding information base (FIB) to identify a port, wherein the FIB associates directories with ports of the switch, and forwarding the client request toward a server containing the file via the identified port, wherein the server is one of a plurality of servers in the distributed storage system.