Storage Management via Address Mapping Profiles and Cache Indexing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing address mapping table, which records the relationship between logical and physical block addresses, is typically large and stored on a non-volatile storage device, making it difficult for quick access due to its size exceeding memory capacity and dynamic changes in mapping during operation.
Innovation Solution
A method and device for storage management that involves creating profiles for address mapping, including a logical address, physical starting address, and a modification flag bit, which are stored in a cache in order of logical starting addresses, along with creating an index for these profiles to improve lookup efficiency and memory utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the address mapping table is stored on a non-volatile storage device, then storage capacity is sufficient, but access speed is slow
Solution Approach 1:
The address mapping table is segmented into multiple profiles, each representing a portion of the mapping table. These profiles are distributed across different storage locations (cache and non-volatile storage), allowing parallel access and reducing the time to retrieve complete mapping information.
Solution Approach 2:
A cache memory is introduced as an intermediary between the non-volatile storage device and the processing unit. Frequently accessed profile data is cached in this intermediate storage layer, providing fast access while maintaining the ability to store large volumes of data on the non-volatile device.
2Speed
If the address mapping table is stored in cache memory, then access speed is fast, but storage capacity is insufficient
Solution Approach 1:
The complete address mapping table is divided into multiple smaller profiles that can fit within cache memory. This segmentation allows the system to store more total mapping data than would fit in cache alone, while still benefiting from fast cache access for individual profiles.
Solution Approach 2:
The profile structure nests multiple levels of information: individual logical-to-physical block mappings are nested within profiles, which are nested within the overall address mapping table. This hierarchical nesting allows efficient organization and retrieval of large volumes of mapping data.
3Adaptability or versatility
If the address mapping table is made dynamic to handle changes, then adaptability is improved, but access complexity increases
Solution Approach 1:
The system includes automatic detection mechanisms that monitor for changes in the address mapping table. When changes are detected, the system automatically updates the affected profiles and invalidates cached entries, eliminating the need for manual intervention and reducing operational complexity.
Solution Approach 2:
The system implements feedback mechanisms where access patterns and change events are monitored. This feedback drives automatic profile updates and cache management, allowing the system to adapt to changing conditions while maintaining simple access patterns for applications.
4Quantity of substance
If the address mapping table is made large to cover all logical blocks, then mapping coverage is complete, but access time increases
Solution Approach 1:
The complete address mapping table is segmented into multiple profiles organized in a hierarchical structure. This segmentation allows the system to maintain comprehensive mapping coverage while enabling selective loading and caching of only the relevant profile portions needed for current operations.
Solution Approach 2:
The system pre-loads and caches profiles that are likely to be accessed based on access patterns and metadata. This preliminary action ensures that frequently needed mapping data is already in fast cache memory when needed, reducing access time while maintaining complete mapping coverage in the full table.
Data Source
AI summary
In a method and apparatus for storage management, a method includes: creating a plurality of profiles for address mapping, the profiles comprising a part of mapping relation in the total mapping table and creating an index for a part of the plurality of profiles to accelerate the lookup speed. A corresponding device and computer program product are also disclosed.