Disk Array Control Device for Discrete Data Write Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current RAID 5 and 6 systems face inefficiencies in data write operations, particularly when dealing with discrete data, as they require multiple commands and increased processing time due to the need to read and update data and parity across multiple disks, leading to higher overhead in command processing and potential errors during data recovery.
Innovation Solution
The implementation of a disk array device with a control unit that determines whether new data is discrete or continuous, allowing for the selection of optimal write methods such as fill small write or fill read bandwidth write, which reduces the number of processing commands and improves write speed by generating new parity using XOR calculations and storing it efficiently across disks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional RAID 5 or 6 write operations are used for discrete data, then data redundancy is maintained, but the number of processing commands increases and write speed decreases
Solution Approach 1:
The system dynamically selects between different write methods (first write method for continuous data, second write method for discrete data) based on the characteristics of the incoming data. This dynamic adaptation allows the system to optimize write performance for discrete data while maintaining appropriate redundancy protection, resolving the contradiction between reliability and productivity.
Solution Approach 2:
The invention changes the operational parameters of the write operation based on data characteristics. When discrete data is detected, the system switches to a specialized write method that modifies how parity is calculated and written, reducing the number of commands required while maintaining data redundancy through alternative parity generation strategies.
2Reliability
If traditional RAID write operations are used for discrete data, then data protection is ensured, but command processing overhead increases
Solution Approach 1:
The invention segments the write operation into distinct paths based on data characteristics. By identifying discrete data and routing it through a specialized write method, the system reduces command processing overhead for this specific segment while maintaining data protection. The segmentation allows traditional write methods to continue handling continuous data without modification.
Solution Approach 2:
The control device acts as an intermediary that detects data characteristics and selects appropriate write methods. This intermediary function reduces command processing overhead by preventing discrete data from undergoing the full traditional write sequence, while still ensuring data protection through the alternative second write method.
3Reliability
If multiple commands are used for discrete data writes, then data integrity can be verified, but processing time increases
Solution Approach 1:
The system dynamically adjusts the verification process based on data characteristics. For discrete data, the specialized write method implements optimized integrity verification that reduces processing time compared to the traditional multi-command approach, while still ensuring data integrity through alternative verification mechanisms.
Solution Approach 2:
The invention changes the verification parameters when handling discrete data. Instead of using the standard multi-command verification sequence, the system applies optimized verification parameters in the second write method that maintain data integrity checks while reducing the time required for verification.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach reduces the number of processing commands and improves write speed by optimizing data and parity updates, enhancing data integrity and recovery processes, especially when dealing with discrete data, thereby improving overall system efficiency and reliability.
Implementation Method 1
generating new parity using XOR calculations and storing it efficiently across disks
Data Source
AI summary
A disk array device includes: a plurality of disk devices including a strip that stores divided data or a parity; a control device to divide the stripe for each of the plurality of disk devices into the divided data having a size of the strip and write the divided data; and a memory to store new data that corresponds to the divided data stored in the strip, wherein the control device detects whether or not the new data is discrete and performs a first write operation or a second write operation when the new data is discrete.