Primary Slice File Recovery with Checksummed Dead Replicas
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to effectively recover a primary slice file affected by storage device errors when there are no live replica slice files available, leading to unacceptable data loss due to the use of stale data from dead replica slice files.
Innovation Solution
The recovery of the primary slice file is achieved by utilizing dead replica slice files through an automated process that programmatically identifies and uses up-to-date, non-stale data by comparing checksums between the primary and dead replica slice files, allowing for the repair of corrupted blocks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If dead replica slice files are used for recovery, then recovery capability is improved, but data integrity deteriorates due to stale data
Solution Approach 1:
The system performs preliminary actions by maintaining multiple replica slice files that are periodically updated with checksums before failures occur. When a failure is detected, the system has pre-computed checksums of replica slice files at different points in time, enabling it to identify which replicas contain valid data before initiating recovery, thus preventing the use of stale data while ensuring recovery capability.
Solution Approach 2:
The system implements feedback mechanisms through checksum verification and monitoring of replica slice file integrity. By continuously comparing checksums of replica files against each other and against the primary slice file, the system receives feedback about data validity, allowing it to automatically identify and use only non-stale data during recovery operations, thereby maintaining data integrity while enabling recovery.
2Loss of information
If manual intervention is required for recovery, then data integrity can be maintained, but productivity deteriorates due to manual operations
Solution Approach 1:
The system performs self-service recovery operations by automatically detecting storage device failures, identifying valid replica slice files through checksum comparison, and initiating recovery processes without requiring manual intervention. The system autonomously manages the entire recovery process, from failure detection to data restoration, thereby maintaining data integrity through automated checksum verification while significantly improving productivity by eliminating manual operations.
3Loss of information
If live replica slice files are used, then data integrity is maintained, but device complexity increases when no live replicas are available
Solution Approach 1:
The system changes the parameter of replica file status from binary (live/dead) to multi-state by introducing checksum-based validity assessment. Instead of simply marking replicas as live or dead, the system computes and compares checksums to determine the actual validity of replica data, allowing it to identify usable replicas even among those marked as dead. This parameter change enables the system to maintain data integrity while reducing the complexity of replica management by providing a clear, objective criterion for replica selection.
Data Source
AI summary
Techniques are provided for repairing a primary slice file, affected by a storage device error, by using one or more dead replica slice files. The primary slice file is used by a node of a distributed storage architecture as an indirection layer between storage containers (e.g., a volume or LUN) and physical storage where data is physically stored. To improve resiliency of the distributed storage architecture, changes to the primary slice file are replicated to replica slice files hosted by other nodes. If a replica slice file falls out of sync with the primary slice file, then the replica slice file is considered dead (out of sync) and could potentially comprise stale data. If a storage device error affects blocks storing data of the primary slice file, then the techniques provided herein can repair the primary slice file using non-stale data from one or more dead replica slice files.