RAID Control Device Data Redistribution for Transient Storage Failures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In storage systems using RAID technology, transiently out-of-service storage servers can cause data loss when they permanently join the system again if another storage device becomes out of service shortly after, due to insufficient redundancy handling.
Innovation Solution
A method for writing data into a storage system that selects appropriate replacements for transiently out-of-service storage devices, ensuring that when another device becomes permanently out of service, the number of out-of-service members does not exceed the tolerable limit, by using a control device to determine and update data stripe members on remaining active devices and write target data to additional storage devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a storage server is allowed to transiently go out of service and rejoin the system, then system availability is improved, but data reliability deteriorates when another device fails shortly after
Solution Approach 1:
The system performs preliminary actions by identifying replacement storage devices before the transiently out-of-service device rejoins. When a device goes out of service, the system proactively selects replacement devices and prepares them in advance, so that when the original device returns and another device fails, the data can be reliably reconstructed using the pre-positioned replacements.
Solution Approach 2:
The system applies preliminary anti-action by preemptively allocating replacement storage devices to counteract the potential data loss risk. Before the transiently out-of-service device rejoins and before any permanent failure occurs, the system has already designated backup devices, thereby preventing the harmful effect of data loss.
2Device complexity
If data is distributed across fewer storage devices, then device complexity is reduced, but data reliability deteriorates when devices go out of service
Solution Approach 1:
The system segments the data striping units across storage devices and implements a hierarchical replacement strategy. By dividing the replacement selection into different levels (first replacement devices, then second replacement devices), the system manages complexity while maintaining reliability through structured data distribution and recovery segments.
Solution Approach 2:
The system applies local quality by treating different storage devices differently based on their roles. Replacement devices are selected with specific characteristics (available capacity, performance) to locally optimize the recovery capability, rather than treating all devices uniformly, thereby maintaining reliability without excessive complexity.
3Adaptability or versatility
If replacement storage devices are selected from all available devices, then adaptability is improved, but data reliability deteriorates due to insufficient redundancy
Solution Approach 1:
The system implements a dynamic two-stage replacement selection process. First, replacement devices are selected when a device goes out of service; then, when the transient device rejoins and another fails, second replacement devices are selected from the remaining devices. This dynamic, staged approach adapts to changing system conditions while ensuring sufficient redundancy for data reliability.
Solution Approach 2:
The system performs preliminary selection of replacement devices in the first stage, establishing a foundation for reliability. This preliminary action creates a buffer of redundancy that can be utilized in the second stage when additional failures occur, balancing adaptability with reliability through phased device selection.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Embodiments of the present invention provide a method for writing data into a storage system and a storage system. The storage system includes a redundant array of independent disks (RAID). The RAID includes a control device and X storage devices, a data stripe stripe is stored in the RAID, and the stripe includes T members. The control device determines that at least one first storage device of the X storage devices is out of service, where at least one member is stored in the first storage device; selects a second storage device from the X storage devices, where a quantity of members stored in the second storage device is less than T/X; and then writes target data into the second storage device, where the target data is a data unit or a check unit used to update the at least one member that is stored in the first storage device. This can ensure data reliability to an extent.