Virtualized Grid Consistency Group for Data Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data protection systems face challenges in minimizing downtime during recovery and ensuring continuous data protection, particularly in keeping pace with high data transaction rates at production sites, leading to potential shutdowns and data loss.
Innovation Solution
The implementation of a virtualized grid consistency group across multiple data protection appliances, which splits input/output operations and uses unique bookmarks to manage data replication and journaling, allowing for dynamic load balancing and efficient data recovery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If journaling is used to enable continuous data protection and rollback capability, then data recovery flexibility is improved, but system overhead increases and may force production site shutdown
Solution Approach 1:
The patent segments the consistency group into multiple subsets and distributes journaling operations across multiple data protection appliances. Each appliance handles a specific subset of logical units, dividing the overhead burden so that no single appliance becomes a bottleneck that would force production shutdown. This segmentation allows the system to maintain high data transaction rates while providing continuous protection.
2Device complexity
If a single data protection appliance handles all replication tasks, then system complexity is reduced, but the ability to keep pace with high data transaction rates deteriorates
Solution Approach 1:
The patent merges multiple data protection appliances into a coordinated system that handles replication collectively. The virtualized consistency group spans across these appliances, combining their processing capabilities to achieve high replication speeds that match production data transaction rates, while maintaining manageable complexity through virtualization abstraction.
3Quantity of substance
If data is backed up on a periodic basis, then storage cost is reduced, but data loss in event of disaster increases
Solution Approach 1:
The patent implements continuous data protection by maintaining constant journaling operations that track every data transaction in real-time. This continuous action ensures that no data is lost even at high transaction rates, while the journal's efficient structure allows for point-in-time recovery without requiring excessive storage capacity beyond what would be used for periodic backups.
4Device complexity
If backup site processes all data transactions sequentially, then device complexity is minimized, but recovery time increases
Solution Approach 1:
The patent segments the data transaction processing across multiple data protection appliances, each handling specific subsets of logical units in parallel. This segmentation enables simultaneous processing of multiple data streams, dramatically reducing recovery time while maintaining manageable device complexity through the virtualized consistency group abstraction that coordinates the parallel operations.
Data Source
AI summary
In one aspect, a method includes forming a virtualized grid consistency group to replicate logical units, running a first grid copy on a first data protection appliance (DPA), running a second grid copy on a second DPA, splitting to the first DPA IOs intended for a first subset of the logical units and splitting to the second DPA IOs intended for a second subset of the logical units different from the first subset of logical units.