Compression Block I/O Reduction via Grouped Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current disk compression technologies generate excessive Input/Output (I/O) operations when writing data larger than the compressed block size, leading to inefficiencies in random access and performance, as multiple blocks are written separately, and increasing the block size results in large compression blocks with negative effects on memory and performance.
Innovation Solution
Data blocks are arranged into groups and sequentially ordered to provide a single I/O operation, with lists indicating available block space organized in advance to allocate continuous blocks for a single command, allowing multiple compressed blocks to be written as one I/O operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the block size is increased to reduce the number of I/O operations, then I/O efficiency is improved, but random access performance and memory usage deteriorate
Solution Approach 1:
The patent segments the write operation into multiple compressed blocks, each with its own dictionary, allowing independent decompression and random access to individual blocks while maintaining efficient I/O through batched writing of these segmented blocks
Solution Approach 2:
The patent merges multiple compressed blocks into a single I/O operation for writing to disk, reducing the total number of I/O operations while maintaining the ability to access individual blocks randomly through the segmentation structure
2Ease of operation
If multiple compressed blocks are written separately, then random access is simplified, but I/O operations increase excessively
Solution Approach 1:
The data is segmented into multiple compressed blocks that can be accessed independently, maintaining random access simplicity while allowing batched I/O operations to write multiple blocks together
Solution Approach 2:
The patent enables continuous writing of multiple compressed blocks in a single I/O operation, eliminating the interruption of separate I/O operations while maintaining the structural integrity and independent accessibility of each block
Data Source
AI summary
Exemplary system and computer program product embodiments compression blocks input/output (I/O) reduction are provided. In one embodiment, by way of example only, data blocks are arranged into groups to provide a single I/O. Lists indicating the available block space for the data blocks are organized in advance according to space size. The data blocks required for a single command are allocated as the single I/O. The data blocks are sequentially ordered. Additional system and computer program product embodiments are disclosed and provide related advantages.