Magnetic Disk Controller Header Separation for Compressed Data Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Magnetic disk devices face difficulties in searching for compressed data stored in buffer memory due to varying data sizes resulting from different compression ratios, making it challenging to manage and retrieve compressed data efficiently.
Innovation Solution
The magnetic disk device employs a controller to generate headers for compressed data groups, stores compressed data in one area, and headers in a separate area, allowing for efficient management by using header information to determine data structure and location within the buffer memory.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If compressed data is stored in buffer memory with varying compression ratios, then data storage efficiency is improved, but data retrieval difficulty increases
Solution Approach 1:
The patent introduces a header as an intermediary element that contains metadata about the compressed data (original size, compressed size, compression ratio). This header acts as a mediator between the variable-length compressed data and the fixed-structure buffer memory, enabling efficient retrieval without compromising storage efficiency
Solution Approach 2:
The patent segments the data structure into distinct components: a fixed-size header containing metadata and a variable-size compressed data body. This segmentation allows the system to maintain efficient fixed-structure storage while accommodating variable compression ratios, and enables easy retrieval by first reading the header to obtain positioning information
2Adaptability or versatility
If compressed data with varying sizes is sequentially stored in buffer memory, then storage flexibility is improved, but searchability deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing key metadata (original data size, compressed data size, compression ratio) in the header before the actual compressed data is stored in the buffer. This preliminary organization of information enables fast search and retrieval operations without requiring sequential scanning of the entire buffer memory
Data Source
AI summary
According to one embodiment, a magnetic disk device includes a memory including a first storage area and a second storage area different from the first storage area, and a controller configured to generate a compressed data compressing input data, generate a header data related to a compressed data group including a plurality of compressed data, generate a packet data including the compressed data group and the header data, store the packet data in the first storage area, and store the header data in the second storage area.