Fast File Server Parallel Data Transfer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional file servers and network attached storage (NAS) devices experience slow data transfer speeds over networks, even when using high-speed connections like Gigabit-Ethernet, due to the limitations of network file systems such as SMB/CIFS.
Innovation Solution
The implementation of a fast file server (FFS) system that utilizes multiple network pathways for parallel data transfer, along with a configuration file that identifies network interfaces and security keys for secure and efficient data access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional network file systems (SMB/CIFS) are used for file access, then compatibility and ease of operation are improved, but data transfer speed deteriorates
Solution Approach 1:
The patent segments the data transfer process by implementing a dual-path architecture: a control path using traditional SMB/CIFS for compatibility and a data path using RDMA for high-speed transfer. This segmentation allows each path to be optimized for its specific function while working together to resolve the contradiction between compatibility and speed.
Solution Approach 2:
The patent introduces an intermediary component (the fast file server software layer) that sits between the traditional file system interface and the storage hardware. This intermediary translates traditional file access requests into optimized data transfer operations using multiple network pathways and RDMA, thereby maintaining compatibility while achieving high-speed transfer.
2Speed
If multiple network pathways are used for parallel data transfer, then data transfer speed is improved, but system complexity increases
Solution Approach 1:
The patent implements self-service mechanisms where the fast file server software automatically discovers available network interfaces, configures appropriate pathways, and manages load distribution across multiple connections. This automation eliminates the need for manual configuration and reduces operational complexity despite using multiple network pathways.
Solution Approach 2:
The patent dynamically adjusts transfer parameters such as pathway selection, parallelism degree, and buffer sizes based on real-time network conditions and workload characteristics. This adaptive parameter adjustment optimizes performance while simplifying management by removing the need for fixed, complex configurations.
3Productivity
If RAID systems are used for storage, then read performance is improved, but the gap between storage performance and network access performance widens
Solution Approach 1:
The patent addresses the performance gap by adding another dimension to data transfer—the network layer. Instead of being constrained by single-path network limitations, the system uses multiple network pathways in parallel, effectively creating a multi-dimensional transfer architecture that matches the parallelism capability of RAID systems and eliminates the performance bottleneck.
Data Source
AI summary
The invention provides, in one aspect, an improved system for data access comprising a file server that is coupled to a client device or application executing thereon via one or more networks. The server comprises static storage that is organized in one or more directories, each containing, zero, one or more files. The server also comprises a file system operable, in cooperation with a file system on the client device, to provide authorized applications executing on the client device access to those directories and/or files. Fast file server (FFS) software or other functionality executing on or in connection with the server responds to requests received from the client by transferring requested data to the client device over multiple network pathways. That data can comprise, for example, directory trees, files (or portions thereof), and so forth.