Triangular Asynchronous Replication Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data replication systems, such as synchronous and asynchronous RDF systems, face challenges with high latency and data consistency issues, especially when transferring data between distant storage devices, and existing solutions like SAR processes incur significant overhead and data loss during failures.
Innovation Solution
Implementing a triangular asynchronous replication system that swaps primary and backup groups between data centers, establishing data mirroring relationships, and initiating multisession control to ensure synchronous and asynchronous mirroring, thereby reducing latency and ensuring data consistency across storage devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If synchronous RDF transfer is used to ensure data consistency between primary and secondary storage devices, then data reliability is improved, but write latency increases due to waiting for acknowledgment
Solution Approach 1:
The system segments the replication architecture into three distinct data centers (first data center with primary group, second data center with synchronous backup group, third data center with asynchronous backup group), allowing different replication strategies to be applied to different segments. This segmentation enables the primary-secondary pair to use synchronous replication for data consistency while the primary-tertiary pair uses asynchronous replication to reduce latency overhead.
Solution Approach 2:
The patent applies different replication qualities to different backup relationships: synchronous replication is applied locally between the primary storage device and secondary storage device to ensure data consistency, while asynchronous replication is applied to the tertiary storage device to minimize latency impact on write operations.
2Productivity
If asynchronous RDF transfer is used to reduce write latency, then write speed is improved, but data consistency between primary and secondary storage devices deteriorates
Solution Approach 1:
The replication system is segmented into synchronous and asynchronous pathways, where critical data consistency requirements are met through synchronous replication between primary and secondary devices, while non-critical backups use asynchronous replication to maintain write speed.
Solution Approach 2:
Different consistency qualities are applied locally: high consistency (synchronous) for the primary-secondary relationship where data integrity is paramount, and lower consistency (asynchronous) for the primary-tertiary relationship where write performance is prioritized.
3Loss of time
If semi-synchronous RDF transfer is used to acknowledge writes immediately, then write latency is reduced, but data integrity is compromised because previous transfers must be acknowledged before new transfers begin
Solution Approach 1:
The system segments the backup architecture into multiple independent replication streams (synchronous stream to secondary device, asynchronous stream to tertiary device), eliminating the bottleneck where one transfer must wait for acknowledgment before the next begins.
Solution Approach 2:
The asynchronous replication pathway performs preliminary data copying to the tertiary storage device without waiting for acknowledgment, allowing write operations to proceed immediately while data integrity is maintained through the synchronous pathway to the secondary device.
4Reliability
If data is transferred over long distances between primary and secondary storage devices, then geographic redundancy is improved, but transmission delay increases causing unacceptable latency
Solution Approach 1:
The long-distance replication is segmented into two independent pathways: a synchronous pathway for critical data consistency over shorter distances, and an asynchronous pathway for geographic redundancy over longer distances, eliminating the constraint that geographic redundancy must wait for slow transmission.
Solution Approach 2:
Different transmission qualities are applied to different geographic scenarios: synchronous transmission for nearby data centers requiring high consistency, and asynchronous transmission for distant data centers where geographic redundancy is prioritized over transmission speed.
Data Source
AI summary
Handling failure of a primary group at a first data center that is part of plurality of data centers providing triangular asynchronous replication, includes creating a data mirroring relationship between at least one storage volume at a second data center having a synchronous backup group that is part of the plurality of data centers and at least one storage volume at a third data center having an asynchronous backup group that is part of the plurality of data centers and resuming work at the second data center. Handling failure of a primary group at a first data center may also include synchronizing the at least one storage volume at the second data center with the at least one storage volume at the third data center prior to resuming work at the second data center.