Pseudo-File-System Driver for Tiered Deduplication Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing file systems used by applications or virtual machines often run out of storage capacity, necessitating costly maintenance and downtime, as they are typically sized based on initial estimates that do not account for data growth.
Innovation Solution
A pseudo-file-system driver leverages deduplication infrastructure to provide a virtually unlimited storage capacity by intercepting write and read requests, moving excess data to secondary storage and restoring it as needed, making the file system appear infinite to the application or virtual machine.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If file system is sized based on initial estimates and stored on high-speed local storage, then access speed is improved, but storage capacity is limited and requires costly maintenance when data grows
Solution Approach 1:
The patent segments the file system into two parts: a local cache portion stored on high-speed local storage and a remote portion stored on slower but cheaper remote storage. The pseudo file system driver manages this segmentation by interceptting I/O requests and determining whether to serve data from the local cache or the remote storage, thereby achieving both fast access for frequently used data and unlimited capacity for growing data needs.
Solution Approach 2:
The patent implements a nested structure where the pseudo file system driver is embedded within the operating system's file system layer, which itself is nested within the application layer. This nested architecture allows the pseudo file system driver to transparently intercept and manage I/O requests between the application and the segmented storage system, presenting a unified file system interface to applications while handling the complexity of distributed storage management.
2Quantity of substance
If file system storage capacity is increased to accommodate data growth, then storage capacity is improved, but maintenance cost and downtime increase
Solution Approach 1:
The patent implements preliminary action by pre-configuring the file system with the pseudo file system driver that establishes the segmented storage architecture in advance. This preliminary setup allows the system to automatically handle data growth by directing new data to remote storage without requiring later maintenance interventions, expansions, or downtime. The deduplication infrastructure is also pre-established to efficiently manage remote storage resources.
Solution Approach 2:
The patent enables self-service through the pseudo file system driver that automatically manages the segmented storage system without human intervention. The driver autonomously intercepts I/O requests, determines optimal storage locations, handles data movement between local and remote storage, and manages the deduplication process. This automation eliminates the need for manual maintenance, capacity planning, and system downtime for storage management tasks.
3Quantity of substance
If deduplication is used to reduce storage costs, then storage cost is reduced, but system complexity increases
Solution Approach 1:
The patent introduces the pseudo file system driver as an intermediary layer between the application and the segmented storage system. This intermediary driver handles the complexity of deduplication operations, data movement, and storage management transparently. By placing the deduplication logic in the pseudo file system driver rather than requiring changes to applications or the underlying storage hardware, the system achieves storage efficiency through deduplication while isolating system complexity within the driver layer.
Data Source
AI summary
An illustrative pseudo-file-system driver uses deduplication functionality and resources in a storage management system to provide an application and/or a virtual machine with access to a locally-stored file system. From the perspective of the application/virtual machine, the file system appears to be of virtually unlimited capacity. The pseudo-file-system driver instantiates the file system in primary storage, e.g., configured on a local disk. The application/virtual machine requires no configured settings or limits for the file system's storage capacity and may thus treat the file system as “infinite.” The pseudo-file-system driver intercepts write requests and may use the deduplication infrastructure in the storage management system to offload excess data from local primary storage to deduplicated secondary storage, based on a deduplication database. The pseudo-file-system driver also intercepts read requests and in response may restore data from deduplicated secondary storage to primary storage, also based on the deduplication database.