Snapshot-Aware Storage Tier Selection to Reduce Controller Redundancy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional storage systems face inefficiencies due to redundant processes performed by both higher-level and lower-level controllers, leading to increased latency and resource utilization.
Innovation Solution
Implementing a direct-mapped flash storage system that addresses data blocks directly without intermediate translation by storage controllers, thereby centralizing data management operations at the operating system level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional storage systems use both higher-level and lower-level controllers to manage data blocks, then data management functionality is distributed, but redundant operations occur and system performance deteriorates
Solution Approach 1:
The patent extracts the data management functionality from the lower-level storage controller and consolidates it at the operating system level. The F2FS file system implements direct addressing of flash storage blocks without requiring translation by the storage controller, thereby eliminating redundant operations and improving system performance while maintaining distributed data management capabilities
Solution Approach 2:
The patent merges the data management responsibilities of higher-level and lower-level controllers into a single unified management layer at the operating system level. By combining these functions, the system eliminates redundant operations between controllers and reduces latency, achieving both functional integration and performance improvement
2Adaptability or versatility
If traditional storage systems perform address translation through storage controllers, then data block addressing is flexible, but write operations increase and reliability decreases
Solution Approach 1:
The patent implements preliminary action by pre-calculating and storing the physical block addresses in the F2FS file system metadata. When data needs to be written, the system directly uses these pre-computed addresses without requiring real-time translation through the storage controller, thereby reducing the number of write operations and improving reliability
Solution Approach 2:
The patent introduces the F2FS file system as an intermediary layer between the application and the flash storage device. This intermediary maintains its own address mapping structures and directly manages data block placement, eliminating the need for the storage controller to perform address translation and reducing redundant write operations
3Device complexity
If storage controllers perform intermediate translation of data blocks, then data management is decentralized, but resource utilization increases and efficiency decreases
Solution Approach 1:
The patent extracts the address translation and data management functions from the storage controller and relocates them to the operating system's file system layer. This extraction eliminates redundant processing at the controller level and improves resource utilization efficiency while maintaining a decentralized data management structure through the F2FS file system
Solution Approach 2:
The patent inverts the traditional storage architecture by placing the intelligence and management functions at the higher-level operating system rather than the lower-level storage controller. This inversion allows the file system to directly manage data blocks using its own addressing scheme, eliminating inefficient intermediate translation and improving overall system efficiency
Data Source
AI summary
Selecting storage resources based on data characteristics, including: determining, for data that is stored within a storage system that includes multiple types of data storage, a storage type to use for the data, wherein: the data is associated with one more snapshots that are stored in the storage system, and the determination is based on whether the data that is stored in at least one volume in the storage system, wherein one storage type is selected if the data is stored in at least one volume and another storage type is selected if the data is not stored in at least one volume; and storing the data in a storage device associated with the determined storage type.