Replica File System Updates Using Block-Object Point-in-Time Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage systems face inefficiencies in data management and reliability, particularly in flash storage systems, due to redundant write operations and lack of direct control by the operating system, leading to reduced reliability and increased wear on storage devices.
Innovation Solution
Implementing a direct-mapped flash storage system where the operating system directly addresses data blocks without translation by storage controllers, managing allocation units and controlling processes such as data rewriting and erasure, thereby reducing unnecessary write operations and enhancing reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If storage controllers translate data block addresses to physical locations, then data management is automated, but redundant write operations increase and reliability decreases
Solution Approach 1:
The patent extracts the address translation function from the storage controller and places it directly in the operating system. The OS maintains a translation layer that maps logical data block addresses to physical flash memory locations, eliminating the controller's intermediary role and the redundant writes it generates.
Solution Approach 2:
The operating system serves itself by implementing direct address translation and data management without relying on storage controller translation. The OS directly manages allocation units, handles wear leveling, and performs erasure operations, making the storage system self-sufficient and reducing controller-induced redundancy.
2Ease of operation
If storage controllers manage data rewriting and erasure, then storage operations are simplified, but wear on flash drives increases
Solution Approach 1:
The patent introduces the operating system as an intermediary between the application layer and the flash storage hardware. The OS implements a file system that directly manages data placement, rewriting, and erasure operations, acting as a intelligent mediator that optimizes these operations to minimize flash wear while maintaining operational simplicity.
Solution Approach 2:
The system changes the management parameters by having the OS directly control allocation unit sizes, data block placement strategies, and erasure timing. This allows dynamic adjustment of these parameters to optimize both operational simplicity and flash drive longevity, rather than relying on fixed controller parameters.
3Reliability
If multiple storage controllers are used for redundancy, then reliability improves, but system complexity increases
Solution Approach 1:
The patent merges the functions of multiple storage controllers into a single operating system-level management layer. Instead of having multiple independent controllers that each perform address translation and data management, the OS consolidates these functions, eliminating the need for multiple controllers while maintaining or improving reliability through software-based redundancy and error handling.
Data Source
AI summary
Methods and systems for transitioning a replica of a file system are described. An illustrative method includes updating a replica file system on a target data repository to be a replica of a source file system as the source file system existed on the source data repository at a point in time, where the replica file system is constructed of block objects at the target data repository that store metadata for individual files and directories of the replica file system and support access to blocks of data associated with the files and directories of the target file system at the target data repository, and where the updating includes updating the block objects of the replica file system to be replicas of block objects of the source file system as the block objects of the source file system existed on the source data repository at the point in time.