Data Storage Random-Read Processing with Parallel L2P Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing data storage devices experience delays and additional costs in random read operations due to the repeated extraction of the logical-to-physical (L2P) mapping table for each read request, leading to increased latency and inefficiency.
Innovation Solution
The method and data storage device manage host requests by identifying random read requests and performing L2P mapping table retrieval in parallel with pre-defined processing, allowing for simultaneous fetching of data, thereby reducing latency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the L2P mapping table is fetched for every random read request, then the data can be read accurately, but the latency increases due to repeated extraction operations
Solution Approach 1:
The patent applies preliminary action by fetching the L2P mapping table in advance before the actual data read operation. The controller identifies random read requests and triggers L2P table retrieval parallel to pre-defined processing operations, so the mapping table is ready before it is actually needed for data translation, thereby reducing read latency without compromising data reading accuracy
Solution Approach 2:
The patent implements continuity of useful action by making the L2P mapping table fetch operation continuous and non-blocking. Instead of sequentially waiting for the L2P table to be fetched before processing read requests, the system performs the fetch operation in parallel with other processing tasks, ensuring that useful actions (data processing and mapping table retrieval) occur simultaneously without interruption
2Ease of operation
If the L2P mapping table is extracted multiple times for random read operations, then each read request can be processed independently, but additional costs and inefficiency are incurred
Solution Approach 1:
The patent applies universality by making the L2P mapping table serve multiple purposes simultaneously. Once the L2P table is fetched for one random read request, it is cached and reused for subsequent read requests within the same time window, allowing a single fetch operation to support multiple independent request processing operations, thereby improving productivity while maintaining independent processing capability
Solution Approach 2:
The patent implements discarding and recovering by temporarily caching the L2P mapping table in memory after fetching it, rather than discarding it after a single use. The cached table is recovered and reused for multiple subsequent read operations, reducing the frequency of expensive fetch operations from storage memory while still allowing independent processing of multiple requests
Data Source
AI summary
The disclosure relates to a method and data storage device for managing host requests in the data storage device. The method includes receiving, from a host device, a read request for reading data from the data storage device, identifying a type of the read request, and based on the type of the read request being a random read request, performing one or more first operations related to processing of the read request in parallel with one or more second operations including: fetching a logical block address of the data from the read request; and obtaining a logical-to-physical (L2P) mapping table from a first memory associated with the data storage device, based on the logical block address, the L2P mapping table used for reading the data from the data storage device.