Active Drive Storage Data Stripping and Reconstruction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems with active storage devices face challenges in providing uninterrupted data services during disk failures, as existing data reconstruction methods are not practical in production environments and require significant redundant data for replication, leading to inefficiencies in failure recovery.
Innovation Solution
A method for data stripping, parity computation, and reconstruction is implemented in an active drive storage system, where data is segmented into chunks, parity chunks are generated, and reorganized based on the number of storage devices, allowing for efficient storage and rapid recovery from failures by utilizing erasure codes like INT codes, which can sustain multiple device failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data replication is used to protect against device failure, then system reliability is improved, but the amount of redundant data increases significantly (as large as or multiple times larger than original data)
Solution Approach 1:
The patent segments data into multiple data chunks and distributes them across different storage devices. Instead of creating full replicas of entire datasets, the system divides data into manageable segments that can be reconstructed using erasure codes, significantly reducing redundant data storage requirements while maintaining reliability.
Solution Approach 2:
The patent changes the approach from traditional replication (1:1 data copying) to erasure coding with configurable redundancy ratios. By adjusting coding parameters such as the number of data chunks and parity chunks, the system can optimize the balance between reliability and redundant data quantity according to specific needs.
2Productivity
If offline reconstruction is used for failed device recovery, then data reconstruction can run at full speed, but the storage system must stop replying to client/application server
Solution Approach 1:
The patent enables continuous data service during reconstruction by allowing online reconstruction operations. The system reconstructs failed data chunks in the background while continuing to serve client requests, ensuring uninterrupted data access without requiring offline reconstruction that would halt service.
Solution Approach 2:
The patent pre-distributes data and parity chunks across multiple storage devices in advance, so that when a failure occurs, reconstruction can immediately begin using available parity information without interrupting service. The system is prepared beforehand to handle failures seamlessly.
3Quantity of substance
If erasure codes are implemented to protect against device failure, then redundant data requirements are reduced, but recovery time increases compared to replication
Solution Approach 1:
The patent segments reconstruction operations into parallel tasks that can execute simultaneously across multiple storage devices. By dividing the recovery process into independent chunk reconstructions that run in parallel, the system reduces overall recovery time while maintaining efficient use of reduced redundant data provided by erasure codes.
Data Source
AI summary
A method for data stripping, allocation and reconstruction in an active drive storage system including a plurality of active object storage devices, each of the plurality of active object storage devices including one or more storage devices and a controller is provided. The method includes the controller of the identified one of the plurality of active object storage devices segmenting the received data into a plurality of data chunks and generating one or more parity chunks in response to the plurality of data chunks. The method further includes the controller of the identified one of the plurality of active object storage devices reorganizing the plurality of data chunks and the one or more parity chunks in response to a number of the plurality of data chunks and a number of the one or more of the plurality of active object storage devices into which the received data is to be stored. Finally, the method includes the step of the controller of the identified one of the plurality of active object storage devices storing the plurality of data chunks and the one or more parity chunks into the one or more of the plurality of active object storage devices.