RAID Data Writing Method Reducing Clock Cycles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional RAID writing methods require three clock cycles for data writing, leading to inefficiencies when processing large numbers of data writing commands, resulting in wasted time and reduced system performance.
Innovation Solution
A data writing method for RAID that involves writing segmented data and checking data into disks within two clock cycles, utilizing a first disk, a second disk, and a memory module to perform XOR operations and store data, thereby reducing the number of clock cycles required for data writing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the conventional three-clock writing method is used for RAID, then the data writing process can be completed with standard procedures, but the operation time increases significantly when processing large numbers of data writing commands
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing checking data in the memory module before the actual data writing operation. This allows the checking data to be ready in advance, eliminating the need to perform the checking operation during the writing cycle, thus reducing the clock cycles required from three to two.
Solution Approach 2:
The memory module serves as an intermediary component that stores checking data temporarily. By introducing this intermediate storage, the system can separate the checking data storage from the final disk writing operation, enabling parallel operations and reducing the sequential clock cycles needed for complete data writing.
2Reliability
If three clock cycles are used for RAID data writing, then all data and checking data can be written to disks, but the system performance decreases when handling large data flows
Solution Approach 1:
Checking data is pre-calculated and stored in the memory module before the writing operation begins. This preliminary action ensures that checking data is available when needed without requiring an additional clock cycle for its calculation and storage during the writing process, thus maintaining reliability while improving productivity.
Solution Approach 2:
The writing process is segmented into distinct phases: data writing occurs in one clock cycle while checking data is written in another clock cycle. This segmentation allows the system to optimize each phase independently, ensuring complete data and checking data writing while reducing the total time required compared to a sequential three-clock approach.
3Ease of operation
If the conventional writing method is used, then standard RAID procedures are followed, but the time consumption increases significantly for large data writing commands
Solution Approach 1:
The patent maintains standardized writing procedures while introducing preliminary action through pre-storing checking data in the memory module. This allows the system to follow standard RAID procedures for data and checking data writing while reducing the total clock cycles from three to two, thus maintaining ease of operation while reducing time loss.
Data Source
AI summary
A data writing method for RAID performs at a write cycle including a first clock and a second clock, and cooperates with a first disk, a second disk, a third disk, and a memory module. The disks store a first checking data, a second data, and a second checking data. The memory module stores the second data including a third segmented data and a fourth segmented data and the first checking data stores. First step of the method is during the first clock, writing the fourth segmented data into the second disk, reading the third segmented data from the first disk, and writing the first checking data into the third disk. Then, during the second clock, the second checking data are calculated according to the third segmented data and the fourth segmented data of the second data, and the second checking data are stored in the memory module.