Snapshot-Assisted Synchronous Storage Replication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional disaster recovery solutions, such as storage replication, face inefficiencies in synchronizing data between primary and secondary storage devices, leading to excess data traffic and bandwidth waste during re-synchronization, especially when retention rates differ between devices.
Innovation Solution
Implementing information lifecycle management (ILM) data and snapshots to assist asynchronous and synchronous replication, allowing for delta data replication and identifying common snapshots to roll back storage servers to a previous state, reducing the need for full data re-synchronization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional storage replication is used to ensure data consistency between primary and secondary storage devices, then data reliability is improved, but excess data traffic and bandwidth are consumed during re-synchronization when retention rates differ
Solution Approach 1:
The patent extracts and replicates only the differential data (delta data) between primary and secondary storage devices rather than replicating entire datasets. By identifying and transferring only the changes, the system maintains data consistency while significantly reducing network bandwidth consumption during re-synchronization operations.
Solution Approach 2:
The system performs preliminary actions by maintaining tab and gate information that tracks data differences between storage devices before full re-synchronization is needed. This preliminary tracking allows the system to quickly identify what data needs to be replicated, avoiding unnecessary transmission of already-synchronized data and reducing bandwidth waste.
2Measurement precision
If tab and gate information is maintained to track data differences during replication, then synchronization accuracy is improved, but processing overhead increases due to excess data traffic
Solution Approach 1:
The patent applies partial action by maintaining tab and gate information only for the specific data blocks that have changed or are pending replication, rather than tracking all data. This selective tracking approach achieves accurate synchronization while minimizing the processing overhead associated with monitoring and managing replication state information.
3Stability of the object's composition
If all I/O operations are recorded and held in volatile cache memory before persistence, then data consistency is maintained, but system performance degrades due to processing delays
Solution Approach 1:
The system performs preliminary actions by pre-calculating and maintaining tab and gate information that identifies which data blocks require persistence. This allows the storage system to proceed with I/O operations without waiting for immediate persistence confirmation, improving performance while ensuring data consistency through the tracking mechanism.
Data Source
AI summary
Technologies are described herein for providing snapshot-assisted synchronous replication between a first storage server and a second storage server. For example, a notification is received at the second storage server that the first storage server has resumed operations following a failure. At this time, the first storage server is in a first current state and the second storage server is in a second current state. Upon receiving the notification, a common snapshot is identified between the first storage server and the second storage server. Upon identifying the common snapshot, the first storage server is rolled back from the first current state to a previous state according to the common snapshot, and upon rolling back the first storage server from the first current state to the previous state, the first storage server and the second storage server are resynchronized using the common snapshot.