Hybrid Drive Translation Layer for SSD-HDD Cache Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hybrid drives face challenges in efficiently managing the cache layer between solid-state drives (SSDs) and hard disk drives (HDDs), as the existing flash translation layer (FTL) is sized only for NAND capacity, limiting the mapping of storage capacity and not persistently tracking data locations across both SSD and HDD.
Innovation Solution
A unified translation layer is introduced that maps storage capacity greater than NAND capacity, using 'leaf entries' to indicate the cache state of logical data units, allowing demotion of data from SSD to HDD based on access priority, and employing a sparse mapping scheme to optimize performance by tracking the location and status of data across both SSD and HDD.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a separate mapping scheme is used for SSD and HDD, then the mapping can be simplified for each medium, but the overall system complexity increases and data location tracking becomes less efficient
Solution Approach 1:
The patent combines separate mapping schemes for SSD and HDD into a unified translation layer that manages both storage media. The translation layer uses a single mapping structure with cache state indicators to track data locations across both SSD and HDD, eliminating the need for separate mapping mechanisms and reducing overall system complexity while maintaining efficient data location tracking.
2Quantity of substance
If the FTL is sized only for NAND capacity, then the SSD mapping is optimized, but the hybrid drive cannot efficiently map the entire storage capacity including HDD
Solution Approach 1:
The translation layer is designed as a universal mapping mechanism that handles both SSD and HDD storage capacity. It extends the traditional FTL concept to cover the entire hybrid drive capacity by incorporating cache state indicators that distinguish between SSD-cached data and HDD-stored data, enabling efficient mapping of the complete storage capacity rather than just the NAND portion.
3Productivity
If data is frequently moved between SSD and HDD, then cache optimization is improved, but the overhead for tracking and managing data locations increases
Solution Approach 1:
The translation layer automatically tracks data locations and cache states without requiring external management intervention. It maintains mapping information and cache state indicators internally, enabling automatic data movement decisions between SSD and HDD based on access patterns, thereby optimizing cache performance while minimizing management overhead through self-service mechanisms.
Data Source
AI summary
The implementations described herein provide a hybrid drive with a storage capacity including solid-state drive (NAND) technology and hard disc drive (HDD) technology. A translation layer is stored in the solid-state drive and includes plurality of entries. Each entry of the plurality of entries corresponds to at least one logical data unit and includes a cache state indicating where the data corresponding to the logical data unit is located and whether the data is valid. The translation layer may be a multi-layer map that includes a sparse mapping scheme. In a sparse multi-layer map, entries are leaf entries or non-leaf entries. Leaf entries include a cache state for the corresponding logical data unit(s). Non-leaf entries may include a pointer to a lower level mapping for a plurality of logical data units.