Compressed Address Table Caching for Fast Storage Lookup
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large logical-to-physical address tables in storage systems often cannot be fully loaded into volatile memory, leading to time-consuming searches in non-volatile memory, which degrades random read performance and requires additional volatile memory, increasing system expense and size.
Innovation Solution
A storage system with a controller that caches a compressed version of the logical-to-physical address table in volatile memory, allowing for parallel search of each entry in a deterministic time using a circuitry comprising comparators, an AND gate, subtractor, divider, and adder, reducing the need for excessive control reads.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the entire logical-to-physical address table is loaded into volatile memory, then search speed is improved, but memory capacity requirements increase
Solution Approach 1:
The patent changes the parameter of data representation by encoding the logical-to-physical address table in a compressed format. Instead of storing full address mappings, the system uses differential encoding where only changes from sequential addresses are stored, significantly reducing the memory capacity required while maintaining fast search capabilities through the volatile memory cache.
2Quantity of substance
If only a portion of the address table is loaded into volatile memory, then memory usage is reduced, but search performance degrades
Solution Approach 1:
By transforming the address table into a compressed representation that captures only incremental changes, the patent enables the entire logical-to-physical mapping to be stored in volatile memory even when the original table would be too large. This maintains full search performance while reducing memory usage compared to storing the uncompressed table.
3Productivity
If additional volatile memory is added to the storage system, then search performance is improved, but system cost and size increase
Solution Approach 1:
The patent applies data compression to the address table, which reduces the amount of volatile memory needed to cache the entire mapping. This allows the system to achieve high search performance without adding extensive volatile memory capacity, thereby controlling system size and cost while maintaining productivity.
Data Source
AI summary
A storage system and method for fast lookup in a table-caching database are provided. In one embodiment, a storage system is provided comprising a volatile memory, a non-volatile memory, and a controller. The controller is configured to store, in the volatile memory, a data structure representing a compressed version of a logical-to-physical address table stored in the non-volatile memory; and search the data structure for a physical address associated with a logical address, wherein the controller is configured to find any physical address in the data structure in a fixed amount of time. Other embodiments are provided.