Compressed Block Read Batching for Faster Data Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Merge compression in data storage systems leads to poor data read performance due to the need for multiple read operations and decompression operations on compressed data blocks.
Innovation Solution
A method that merges multiple read requests for consecutive data blocks into a single read request, reducing the number of read and decompression operations by compressing and storing them as a single data block, and caching read data for direct access.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple data blocks are merged and compressed into a single compressed block, then storage space utilization is improved, but data read performance deteriorates due to multiple read and decompression operations
Solution Approach 1:
The patent merges multiple individual read requests into a single batched read request. When multiple data blocks are stored as a compressed block, instead of issuing separate read requests for each block, the system batches multiple read requests together and processes them in a single operation, reducing the total number of read and decompression operations required
Solution Approach 2:
The patent performs preliminary batching of read requests before execution. By collecting and consolidating multiple read requests in advance into a single batched request, the system prepares the optimal read operation structure beforehand, allowing the storage system to process multiple data blocks in one operation rather than sequentially
2Reliability
If multiple read requests are processed separately, then data retrieval accuracy is maintained, but the number of read operations increases reducing overall efficiency
Solution Approach 1:
The patent combines multiple individual read requests into a single batched read request without compromising data retrieval accuracy. The batched request maintains the integrity and correctness of each individual data block retrieval while executing them together in one operation, thus preserving reliability while eliminating the time loss from sequential processing
3Measurement precision
If decompression operations are performed for each read request, then data access precision is maintained, but calculation amount and processing time increase
Solution Approach 1:
The patent merges multiple decompression operations into a single batched decompression process. When multiple data blocks within a compressed block are requested, the system performs one decompression operation to retrieve all required blocks simultaneously, maintaining precise access to each individual block while dramatically reducing the total calculation amount and processing time compared to sequential decompression
Data Source
AI summary
A data read method comprising obtaining a second read request based on P first read requests, wherein the P first read requests are for reading P first data blocks, and wherein P is a positive integer; performing a read operation based on the second read request to obtain Q second data blocks comprising a merged data block, wherein the merged data block is based on compression on at least one of the P first data blocks, and the P first data blocks are some or all of first data blocks for obtaining the Q second data blocks; decompressing the Q second data blocks to obtain data; and obtaining the P first data blocks based on the data.