Nonvolatile Memory Controller Two-Level Address Translation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional de-duplication technologies in solid state drives (SSDs) do not effectively manage storage for management data, leading to inefficiencies in data storage and retrieval, particularly in handling redundant data and garbage collection processes.
Innovation Solution
A memory system with a controller that employs two-level address translation using a logical-to-intermediate address translation table and an intermediate-to-physical address translation table, along with reference count management, to optimize data storage and garbage collection by associating intermediate addresses with logical addresses and physical addresses, thereby reducing redundant data storage and improving storage efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If conventional de-duplication technology is used to store redundant data, then storage capacity is improved, but management data storage efficiency deteriorates due to insufficient consideration of memory source management
Solution Approach 1:
The patent segments the address translation process into two distinct tables: a first translation table for logical-to-physical address mapping and a second translation table for logical-to-intermediate address mapping. This segmentation allows independent optimization of each table's storage management, enabling efficient handling of de-duplication management data while maintaining overall storage capacity.
Solution Approach 2:
The patent introduces an intermediate address as a mediator between logical addresses and physical addresses. This intermediate address serves as a reference key in the second translation table, enabling efficient de-duplication management by storing only intermediate addresses rather than full physical addresses, thus improving management data storage efficiency while preserving storage capacity.
2Device complexity
If a single translation table is used for address mapping, then device complexity is reduced, but garbage collection efficiency deteriorates due to inability to optimize redundant data handling
Solution Approach 1:
The patent divides the single translation table into two separate tables: a first translation table storing logical-to-physical mappings and a second translation table storing logical-to-intermediate mappings. This segmentation enables specialized optimization for garbage collection operations, where the second table's intermediate addresses serve as efficient keys for identifying and consolidating redundant data, thereby improving garbage collection efficiency without excessive complexity increase.
Solution Approach 2:
The patent maintains the first translation table for complete address mapping while adding a second translation table that stores only intermediate addresses for de-duplication purposes. This partial redundancy enables efficient garbage collection operations by providing quick access to intermediate addresses for identifying redundant data, without requiring complete duplication of all address mapping information.
3Loss of substance
If de-duplication is implemented without optimized management data storage, then redundant data reduction is achieved, but write amplification increases due to inefficient garbage collection operations
Solution Approach 1:
The patent uses intermediate addresses as mediators in the second translation table to efficiently manage de-duplication operations. These intermediate addresses serve as compact keys that enable rapid identification of redundant data during garbage collection, reducing the computational overhead and I/O operations required for consolidating duplicate data, thereby reducing write amplification while maintaining effective redundant data reduction.
Solution Approach 2:
The patent changes the parameter representation in the second translation table by storing intermediate addresses instead of full physical addresses. This parameter transformation reduces the storage size of management data and accelerates lookup operations during garbage collection, enabling more efficient redundant data consolidation with reduced write amplification.
Data Source
AI summary
According to one embodiment, a memory system manages a plurality of management tables corresponding to a plurality of first blocks in a nonvolatile memory. Each management table includes a plurality of reference counts corresponding to a plurality of data in a corresponding first block. The memory system copies a set of data included in a copy-source block for garbage collection and corresponding respectively to reference counts belonging to a first reference count range to a first copy-destination block, and copies a set of data included in the copy-source block and corresponding respectively to reference counts belonging to a second reference count range having a lower limit higher than an upper limit of the first reference count range to a second copy-destination block.