NAS Cluster File System via Block Device Abstraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional file systems are not well optimized for cluster deployments, particularly in NAS clusters with multiple data nodes and varying block storage technologies, making it difficult to manage and coordinate storage operations across large numbers of nodes and different block storage solutions.
Innovation Solution
A file system is deployed across multiple nodes in a NAS cluster by discovering a LUN provisioned from block storage, rendering it as a block device, creating a local volume, and deploying the file system on this volume, where each address space corresponds one-to-one, allowing write requests to be propagated efficiently across the LUN, block device, and file system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional file systems tightly coordinate with underlying block storage, then data organization and management are simplified, but scalability across large numbers of data nodes and different block storage technologies is limited
Solution Approach 1:
The patent introduces a block device layer as an intermediary between the file system and underlying block storage. This block device acts as a mediator that abstracts the differences between various block storage technologies (SAN, NAS, cloud-based storage), allowing the file system to operate uniformly without direct coordination complexity with diverse storage systems across multiple data nodes
Solution Approach 2:
The patent segments the storage stack into distinct layers: file system layer, block device layer, and underlying block storage layer. This segmentation allows each layer to operate independently with well-defined interfaces, improving scalability across data nodes while maintaining simplified data organization at the file system level
2Quantity of substance
If conventional file systems are deployed across multiple data nodes, then storage capacity is increased, but management and coordination across nodes becomes difficult
Solution Approach 1:
The block device layer provides a universal interface that works consistently across multiple data nodes and different block storage technologies. This multi-functional abstraction layer enables simplified management operations (provisioning, mounting, data access) to be performed uniformly across the cluster regardless of the underlying storage technology or node configuration
3Reliability
If tight coordination between file system and block storage is maintained, then data integrity is ensured, but scalability to arbitrarily large numbers of nodes is restricted
Solution Approach 1:
The block device intermediary maintains data integrity through well-defined data flow paths and address space mappings while enabling scalability. The one-to-one address correspondence between file system and block device ensures data integrity, while the abstraction from underlying diverse block storage enables deployment across arbitrary numbers of nodes with different storage technologies
Data Source
AI summary
A technique for operating a file system in a NAS (network attached storage) cluster includes discovering, by a data node running in the NAS cluster, a LUN (Logical UNit) provisioned from block storage. The data node renders the LUN as a block device and creates a local volume, built on the block device. The data node then deploys the file system on the local volume. The file system, the local volume, the block device, and the LUN all have address spaces, and the address space of each corresponds one-to-one with the address space of each of the others. Write requests directed to addresses in the file system propagate to the LUN, where they effect writes at corresponding addresses in the LUN.