Active/Active Storage Replication via Virtual Service Layer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data protection systems face challenges in maintaining continuous data protection, particularly in keeping pace with high data transaction rates at production sites without slowing them down, leading to potential site shutdowns due to backlog of un-logged transactions.
Innovation Solution
The integration of journal-based replication with a virtual service layer in an active/active storage system, which enables quiescing IO commands, creating change sets, and transferring data across sites while maintaining write order fidelity, allowing for point-in-time access and recovery without requiring a second copy of data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If journal-based replication is used to maintain continuous data protection, then data recovery capability is improved, but system complexity increases due to overhead of multiple data transactions at backup site
Solution Approach 1:
The patent segments the replication process into distinct phases: quiescing IO commands at the production site, creating change sets, transferring data to backup sites, and unquiescing. This segmentation allows the system to manage complexity by breaking down the continuous replication process into manageable discrete operations.
Solution Approach 2:
The patent introduces a virtual service layer as an intermediary between the production site and backup sites. This intermediary manages the journaling process, coordinates data transactions, and handles the complexity of maintaining write order fidelity across multiple sites, thereby reducing the burden on individual components.
2Reliability
If backup site keeps pace with high data transaction rates, then data protection continuity is improved, but production site performance deteriorates due to forced slowdown
Solution Approach 1:
The patent implements preliminary actions by quiescing IO commands before data replication occurs. This allows the system to prepare the data state, create consistent change sets, and transfer data to backup sites before resuming normal operations, ensuring data protection continuity without requiring the production site to continuously slow down.
Solution Approach 2:
The patent employs periodic quiescing of IO commands rather than continuous slowing. The system periodically pauses data operations at the production site to synchronize with backup sites, then resumes normal high-performance operations. This periodic approach maintains data protection continuity while minimizing impact on overall production performance.
3Quantity of substance
If conventional tape backup is used, then data storage cost is reduced, but recovery time increases and data availability decreases
Solution Approach 1:
The patent implements continuous data replication where backup sites are continuously updated with data changes from the production site. This continuous synchronization eliminates the periodic backup cycles of conventional systems, enabling rapid recovery without lengthy data restoration processes while maintaining cost-effective storage utilization.
Solution Approach 2:
The patent creates and maintains copies of production data at backup sites through continuous replication. These up-to-date copies enable immediate recovery operations without requiring time-consuming data reconstruction, significantly reducing recovery time compared to conventional backup methods.
4Stability of the object's composition
If synchronous replication is implemented, then data consistency is improved, but system performance deteriorates due to waiting for backup confirmation
Solution Approach 1:
The patent segments the replication process into discrete phases with clear boundaries. By quiescing IO commands, creating change sets, and transferring data in distinct steps, the system achieves data consistency without requiring continuous synchronous confirmation, thereby improving overall system performance.
Solution Approach 2:
The patent performs preliminary actions by creating complete change sets before transferring data to backup sites. This preliminary preparation ensures data consistency is achieved through careful planning and execution of discrete operations rather than continuous synchronous validation, reducing performance overhead.
Data Source
AI summary
In a first embodiment, a method and computer program product for use in a storage system comprising quiescing IO commands the sites of an ACTIVE/ACTIVE storage system, the active/active storage system having at least two storage sites communicatively coupled via a virtualization layer, creating a change set, unquiescing IO commands by the virtualization layers, transferring data of a change set to the other sites of the active/active storage system by the virtualization layer, and flushing the data by the virtualization layer.In a second embodiment, a method and computer program product for use in a storage system comprising fracturing a cluster of an active/active storage system; wherein the cluster includes at least two sites, stopping IO on a first site of the cluster; and rolling to a point in time on the first site.