Data Block Extent Sizing for Storage Read/Write Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data copying methods are inefficient due to inadequate utilization of resources over time and improper data block sizes, leading to increased read/write operations and reduced efficiency, especially in large data sets like those found in enterprise databases.
Innovation Solution
The method involves determining a block extent size that is an integral multiple of the read/write unit and copy buffer size, aligning data blocks with these units to minimize read/write operations and optimize the use of storage resources, using the formula P=⌊O+N×M-1/N×M⌋×N to calculate the block extent, ensuring efficient data copying without altering existing hardware configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is divided into blocks using conventional block extent sizes, then data copying can be performed, but the block sizes are improper leading to increased read/write operations and reduced efficiency
Solution Approach 1:
The patent changes the block extent size parameter from conventional values to values that are integral multiples of the underlying storage device's read/write unit size. This parameter adjustment ensures that each data block can be read or written in a single operation, eliminating the need for multiple read/write operations per block and thereby improving copying efficiency while reducing time loss.
2Productivity
If conventional block extent sizes are used, then data copying is possible, but resources are not sufficiently utilized leading to increased read/write operations on hardware devices
Solution Approach 1:
The patent modifies the block extent size parameter to be an integral multiple of the hardware read/write unit size. This ensures optimal utilization of hardware resources by aligning software data structures with hardware operation boundaries, thereby reducing the number of read/write operations required and minimizing energy loss.
3Ease of operation
If data blocks are divided using conventional methods, then copying can proceed, but the block sizes do not align with read/write units causing increased operational overhead
Solution Approach 1:
The patent adjusts the block extent size parameter to match integral multiples of the read/write unit size. This alignment simplifies the copying process by ensuring that each block operation corresponds directly to a single hardware operation, reducing operational complexity and making the system easier to manage.
Data Source
AI summary
Various embodiments of the present invention relate to a method and apparatus for data copy. Specifically, in one embodiment of the present invention there is provided a method for data copy, comprising: obtaining a data source on which data copy is to be executed; determining a size P of a block extent based on which the data source is divided; dividing the data source into at least one data block based on the size P of the block extent; and copying data from the data source to a data target in the basic unit of the at least one data block; wherein the size P of the block extent is an integral multiple of a size R of a read/write unit supported by underlying architecture. In one embodiment of the present invention, there is provided an apparatus for data copy.