RAID Write Back Method for Partial Data Stripe Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
RAID 5 systems face processing speed limitations during partial data stripe updates due to the need for extra processes like reading pre-update data from disks, which slows down write back processing.
Innovation Solution
A write back method for RAID control systems that determines the optimal write method (Small Write or Read & Bandwidth Write) by generating reference values based on update information, reducing the load on the system by comparing the efficiency of both methods and selecting the one with lower resource usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the Small Write method is used for partial data stripe updates, then data redundancy is maintained, but processing speed decreases due to extra read operations from disks
Solution Approach 1:
The patent applies preliminary action by pre-loading data stripes into the cache memory before the write back operation. The controller determines which data stripes to pre-load based on the update information, and performs the pre-loading operation before the actual write back. This allows the write back operation to proceed without waiting for slow disk read operations, thereby improving processing speed while maintaining data redundancy through the Small Write method.
2Speed
If the Read & Bandwidth Write method is used for partial data stripe updates, then processing speed improves by avoiding disk reads, but system load increases due to additional XOR operations
Solution Approach 1:
The patent applies partial action by selectively applying the Read & Bandwidth Write method only to data stripes that are being updated, rather than to all data stripes. The controller determines which data stripes require update based on update information, and applies the optimized write method only to those specific stripes. This reduces the overall system load compared to applying the method universally, while still achieving speed improvements for the updated portions.
3Ease of operation
If all data stripes are updated in the cache memory, then write back processing is simplified without disk reads, but cache memory capacity is consumed
Solution Approach 1:
The patent applies segmentation by dividing the data stripes into different categories based on their update status. The controller identifies which data stripes are being updated and which are not, and handles them differently during the write back operation. Updated data stripes can be written back using simplified methods, while non-updated stripes are handled separately. This segmentation allows the system to maintain simplicity for updated portions without requiring all cache memory capacity to be consumed.
Data Source
AI summary
A RAID control apparatus comprises at least a cache memory; an update information management table for storing update information; an update information storage unit for storing, in the update information management table, update information by detecting a data update; a reference value generation unit for generating a reference value expressing a load of a write back processing by using a Small Write method and a Read & Bandwidth Write method based on the update information; a write method determination unit for determining a write method according to the reference value and a write unit for carrying out a write processing, in order to provide a write back method for a RAID apparatus capable of improving a processing speed at the time of updating even in the case of including the processing of updating a part of data stripes.