Object Storage Synchronous Replication for Zero-RTO Failover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing distributed storage systems face challenges in efficiently synchronizing object storage data across multiple sites, leading to potential data loss and disruption during failures, especially when asynchronous mirroring is used, and lack a zero Recovery Point Objective (RPO) and zero Recovery Time Objective (RTO) business continuity solution.
Innovation Solution
Implementing synchronous replication with aggregate mirroring to ensure that both data and configuration information are consistently replicated across storage clusters, providing zero RPO and zero RTO business continuity by preventing switchover during configuration changes and ensuring data and configuration consistency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If asynchronous mirroring is used for data replication, then device complexity is reduced, but data consistency and reliability deteriorate during failures
Solution Approach 1:
The system performs preliminary actions by initiating an audit job on the first storage cluster before switchover, synchronously replicating audit configuration data and audit data to the second storage cluster in advance. This ensures that the standby cluster has up-to-date data and configuration before it needs to take over, eliminating data consistency issues during failure without requiring complex real-time synchronization mechanisms
Solution Approach 2:
The system implements feedback by monitoring the status of the first storage cluster and automatically triggering switchover to the second storage cluster when failure is detected. The audit job provides feedback on data consistency status, and the system uses this feedback to determine when switchover is safe to perform, ensuring reliability while maintaining manageable complexity
2Productivity
If switchover is performed during configuration changes, then productivity is improved through faster failover, but manufacturing precision deteriorates due to configuration inconsistency
Solution Approach 1:
The system performs preliminary actions by synchronously replicating audit configuration data from the first storage cluster to the second storage cluster before switchover occurs. This ensures that the configuration is already consistent and ready on the standby cluster, allowing immediate failover without configuration inconsistency while maintaining precision
Solution Approach 2:
The system creates an exact copy of the audit configuration data from the first storage cluster to the second storage cluster through synchronous replication. This copy ensures that the standby cluster has identical configuration data, allowing safe switchover during configuration changes without losing consistency, thus maintaining manufacturing precision while enabling fast failover
3Reliability
If synchronous replication is implemented for both data and configuration, then reliability is improved with zero RPO, but device complexity increases
Solution Approach 1:
The system segments the replication process into distinct components: data replication and audit configuration replication. By separating these functions and using an audit job to handle configuration synchronization, the system achieves zero RPO reliability for both data and configuration while managing complexity through modular design. The audit job acts as a separate module that handles configuration synchronization independently from data replication
Data Source
AI summary
In one embodiment, a computer implemented method includes storing objects in a first bucket and storing files in a second bucket of a first storage cluster of the distributed storage system, synchronously replicating data of the objects into a third mirrored bucket of a second storage cluster of the distributed storage system, synchronously replicating OSP configuration data from the first storage cluster to the second storage cluster during the synchronous replication, and providing non-disruptive operations with zero recovery time objective (RTO), and ensuring consistency between the objects in the first bucket and the objects in the third bucket for a software application that is accessing one or more objects and files using the OSP. The objects and files are accessible through an object storage protocol (OSP).